© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 7465
    Prev
    Next
    INDEX
    Explanations

    first person pronouns and prepositions within a short context, possibly indicating someone is grappling with a situation or point in time

    oai_token-act-pair · gemini-2.0-flash

    words or phrases indicating beginnings or introductions

    np_token-act-pair-logits · gpt-4o-mini

    at

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     MonoBehaviour
    -0.82
    TagMode
    -0.79
    ftagPool
    -0.77
    MigrationBuilder
    -0.77
     समीक्षाओं
    -0.77
     سكانية
    -0.75
    principalColumn
    -0.72
     Roskov
    -0.72
     FetchType
    -0.72
     IBOutlet
    -0.71
    POSITIVE LOGITS
    tahui
    0.40
     first
    0.39
     times
    0.37
     nap
    0.37
    oshi
    0.37
     στε
    0.37
    hadap
    0.36
     Further
    0.36
    енко
    0.36
     FURTHER
    0.36
    Activations Density 1.799%

    No Known Activations