© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 13103
    Prev
    Next
    INDEX
    Explanations

    uses the word "to" to transition or introduce another action or explanation

    oai_token-act-pair · gemini-2.0-flash

    terms related to data packets and networking

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

    Travel and movement

    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
     into
    -0.84
     out
    -0.82
     away
    -0.81
     outwards
    -0.81
     down
    -0.77
     back
    -0.76
     onto
    -0.75
     through
    -0.75
     onward
    -0.70
     outward
    -0.68
    POSITIVE LOGITS
     الحره
    0.68
     مرئيه
    0.67
     enters
    0.61
    phosa
    0.60
    WindowConstants
    0.60
    migrationBuilder
    0.59
     فريبيس
    0.58
     ModelExpression
    0.56
    Становништво
    0.56
    BeginContext
    0.54
    Activations Density 4.600%

    No Known Activations