© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 846
    Prev
    Next
    INDEX
    Explanations

    words ending in wise relating to a specific quality

    oai_token-act-pair · gemini-2.0-flash

    -wise suffix

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     betweenstory
    -0.81
    ftant
    -0.79
    ſelf
    -0.75
    rrggbb
    -0.72
     houſe
    -0.71
     Houſe
    -0.69
    jgl
    -0.69
    gonic
    -0.69
    postsleuth
    -0.68
    énario
    -0.68
    POSITIVE LOGITS
    <bos>
    0.69
    ,
    0.61
     obstante
    0.56
     mentally
    0.47
    '
    0.46
    zieży
    0.45
    chism
    0.42
    Today
    0.42
     benne
    0.42
     '
    0.41
    Activations Density 1.676%

    No Known Activations