© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 11107
    Prev
    Next
    INDEX
    Explanations

    academic or legal writing and language

    oai_token-act-pair · gemini-2.0-flash

    legal or medical texts

    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
    ing
    -0.96
     '+':
    -0.81
     //$
    -0.79
     '-':
    -0.74
     refreshToken
    -0.73
    ING
    -0.73
    <bos>
    -0.72
    _',
    -0.72
     @}
    -0.71
    ='';
    -0.71
    POSITIVE LOGITS
    手
    0.75
    kező
    0.70
    submitted
    0.68
    maal
    0.64
    Naissance
    0.63
    AutoScaleMode
    0.63
    ậc
    0.63
    、
    0.63
    WindowConstants
    0.62
    LookAnd
    0.61
    Activations Density 17.862%

    No Known Activations