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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 8-GEMMASCOPE-TRANSCODER-16K
    4. 1395
    Prev
    Next
    INDEX
    Explanations

    scientific publications and citations with emphasis on names and years

    oai_token-act-pair · gemini-2.0-flash

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     InputDecoration
    -0.85
     bezeichneter
    -0.77
    <bos>
    -0.76
    Skocz
    -0.76
    styleable
    -0.75
    脚注の使い方
    -0.75
    lapsingToolbar
    -0.74
    AntiForgeryToken
    -0.74
    RenderAtEndOf
    -0.73
     Numerade
    -0.73
    POSITIVE LOGITS
    <eos>
    0.48
    <b>
    0.40
    </td>
    0.39
    鋒
    0.37
    サート
    0.36
    <strong>
    0.36
     -
    0.35
    humidité
    0.35
    </b>
    0.35
    <h2>
    0.33
    Activations Density 3.545%

    No Known Activations