© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 15100
    Prev
    Next
    INDEX
    Explanations

    a lot of language constructs: pronouns, function words, transitions, and also seems tuned for user-driving.

    oai_token-act-pair · gemini-2.0-flash

    driving

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     تانيه
    -0.73
     numberWith
    -0.72
     CreateTagHelper
    -0.53
     useAppContext
    -0.53
     MainAxisSize
    -0.51
     trụ
    -0.50
     faa
    -0.49
     Samir
    -0.48
     masonry
    -0.48
    endphp
    -0.48
    POSITIVE LOGITS
     drive
    0.56
     park
    0.54
     propOrder
    0.53
    MessageOf
    0.53
    Autoritní
    0.53
    jgl
    0.53
    hikari
    0.52
    +#+
    0.51
    ContentAsync
    0.50
     CYTHON
    0.50
    Activations Density 3.098%

    No Known Activations