© 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
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 7697
    Prev
    Next
    INDEX
    Explanations

    code snippets, particularly variable and function names, often involving underscores

    oai_token-act-pair · gemini-2.0-flash

    underscore

    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
    '
    -1.33
    <bos>
    -1.01
    ↵
    -0.95
    {
    -0.87
    S
    -0.87
    A
    -0.86
    U
    -0.86
    \
    -0.84
    1
    -0.83
    v
    -0.82
    POSITIVE LOGITS
    Cordialement
    1.20
    Amicalement
    1.15
    Lycka
    1.14
    BibitemShut
    1.13
    bibfield
    1.07
    berikut
    1.07
    Atentamente
    1.05
    ^(@)
    1.04
    Grüsse
    1.02
    ratulations
    1.01
    Activations Density 0.962%

    No Known Activations