© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 10042
    Prev
    Next
    INDEX
    Explanations

    code documentation tags

    oai_token-act-pair · gemini-2.0-flash

    summary

    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
    summary
    -1.21
     summary
    -1.13
    Summary
    -0.95
     Summary
    -0.91
     summaries
    -0.82
    SUMMARY
    -0.75
     SUMMARY
    -0.71
     summar
    -0.71
    <bos>
    -0.65
     summarize
    -0.63
    POSITIVE LOGITS
    InputBorder
    1.09
    setVerticalGroup
    0.98
     nakalista
    0.93
    WebControls
    0.93
     CreateTagHelper
    0.92
     resourceCulture
    0.92
    expandindo
    0.91
    tvguidetime
    0.90
    FormTagHelper
    0.90
     صوتيه
    0.90
    Activations Density 0.087%

    No Known Activations