© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 10282
    Prev
    Next
    INDEX
    Explanations

    people having trouble with a program and referencing error messages

    oai_token-act-pair · gemini-2.0-flash

    I

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    setVerticalGroup
    -0.80
    ParallelGroup
    -0.72
    ConstraintMaker
    -0.71
     gynhyrchwyd
    -0.71
     للمعارف
    -0.63
    fromnode
    -0.62
    enterOuterAlt
    -0.59
    GraphicsUnit
    -0.59
    Erreferentziak
    -0.58
    queryInterface
    -0.58
    POSITIVE LOGITS
     keep
    2.95
     kept
    2.86
     Keep
    2.78
     keeps
    2.77
    keep
    2.77
    Keep
    2.77
    kept
    2.63
     keeping
    2.58
     KEEP
    2.56
     Kept
    2.55
    Activations Density 5.724%

    No Known Activations