© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 10845
    Prev
    Next
    INDEX
    Explanations

    words or phrases signifying struggles

    oai_token-act-pair · gemini-2.0-flash

    work and effort

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    I
    -0.50
     ktorí
    -0.45
     skú
    -0.38
     ťaž
    -0.37
    ждый
    -0.35
     voľ
    -0.35
    who
    -0.35
    nos
    -0.35
    gro
    -0.34
     ympä
    -0.34
    POSITIVE LOGITS
     the
    0.87
     незавершена
    0.79
     Cæsar
    0.71
     utafitiHapana
    0.71
    WebElementEntity
    0.70
     betweenstory
    0.69
    Tetapi
    0.68
    ArrowToggle
    0.67
    Билгалдахарш
    0.66
    writeFieldEnd
    0.66
    Activations Density 13.941%

    No Known Activations