© 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. 14701
    Prev
    Next
    INDEX
    Explanations

    the word "reserve," especially when referring to the kidneys

    oai_token-act-pair · gemini-2.0-flash

    reserve

    np_max-act · 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
    ,
    -0.94
     and
    -0.91
     (
    -0.89
     or
    -0.88
    a
    -0.85
    ;
    -0.73
     I
    -0.73
     -
    -0.72
     in
    -0.71
     for
    -0.70
    POSITIVE LOGITS
     Theſe
    1.73
     Monfieur
    1.69
     myſelf
    1.53
     ſeveral
    1.40
     ainfi
    1.39
     Houſe
    1.35
     Efq
    1.34
     Jefus
    1.34
     becauſe
    1.34
     itſelf
    1.34
    Activations Density 2.655%

    No Known Activations