© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 14466
    Prev
    Next
    INDEX
    Explanations

    program code elements and language

    oai_token-act-pair · gemini-2.0-flash

    code configuration

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    createStatement
    -0.68
    ReusableCell
    -0.60
    </caption>
    -0.56
    '>";
    -0.56
    ++];
    -0.56
    </h3>
    -0.53
    --)
    -0.51
    __":
    -0.51
    ."</
    -0.50
     المعيارى
    -0.50
    POSITIVE LOGITS
    <bos>
    0.98
    Portale
    0.90
     /\.(
    0.89
     craindre
    0.70
    ⓘ
    0.68
    balleur
    0.68
    antMatchers
    0.67
    서는
    0.67
     هيا
    0.67
     Haynes
    0.65
    Activations Density 25.971%

    No Known Activations