© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12661
    Prev
    Next
    INDEX
    Explanations

    verbs in the past tense

    oai_token-act-pair · gemini-2.0-flash

    origins/biography

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     was
    -1.00
     wasn
    -0.96
     weren
    -0.90
     had
    -0.89
     were
    -0.87
     hadn
    -0.82
     vardı
    -0.80
     lacked
    -0.80
    wasn
    -0.79
     knew
    -0.79
    POSITIVE LOGITS
    HasForeignKey
    0.76
    клопе
    0.75
    पया
    0.74
     autorytatywna
    0.73
    ########.
    0.71
     للاسماء
    0.71
    ValueStyle
    0.69
     >=",
    0.69
    TypedDataSet
    0.68
    ಿದೆ
    0.68
    Activations Density 5.685%

    No Known Activations