© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 5107
    Prev
    Next
    INDEX
    Explanations

    words related to plans, intentions, or opinions

    oai_token-act-pair · gemini-2.0-flash

    human intentions and actions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    OLO
    -0.49
    GroupLayout
    -0.48
    atung
    -0.48
    taget
    -0.48
    ationen
    -0.48
    hte
    -0.48
    LLOW
    -0.47
     convi
    -0.47
     cré
    -0.47
    Routing
    -0.46
    POSITIVE LOGITS
     ModelExpression
    0.86
    enterOuterAlt
    0.79
    SourceChecksum
    0.79
     Italijani
    0.77
    homonymie
    0.77
    évaluateur
    0.76
    Zunanje
    0.75
    OGND
    0.75
     gynhyrchwyd
    0.74
    RegressionTest
    0.73
    Activations Density 14.735%

    No Known Activations