© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 15407
    Prev
    Next
    INDEX
    Explanations

    instances of the verb "play" and words associated with negotiation or influencing things.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     ſeveral
    -0.84
     avoient
    -0.82
     Majefty
    -0.78
     uſe
    -0.77
     Jefus
    -0.77
     Lippincott
    -0.75
     Pliocene
    -0.75
     vectorielle
    -0.74
     auffi
    -0.73
     fhew
    -0.73
    POSITIVE LOGITS
    <bos>
    1.09
     the
    0.70
     along
    0.64
     and
    0.57
     through
    0.57
     particularly
    0.56
    Presented
    0.55
     for
    0.55
     living
    0.54
     embarking
    0.54
    Activations Density 1.235%

    No Known Activations