© 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. 6765
    Prev
    Next
    INDEX
    Explanations

    the word "cabinet" or numbers

    oai_token-act-pair · gemini-2.0-flash

    cabinet

    np_max-act · gemini-2.0-flash

    say "space" Method used: 2 — tokens mostly start with a space marker, so say "space"

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
    f
    -0.65
    (
    -0.64
    id
    -0.63
    '
    -0.59
    as
    -0.59
    e
    -0.57
    -
    -0.56
    <
    -0.55
    H
    -0.55
    m
    -0.54
    POSITIVE LOGITS
    expandindo
    1.04
    WebElementEntity
    0.95
    TypedDataSet
    0.93
    EDEFAULT
    0.88
     سكانية
    0.87
    awtextra
    0.86
    IBLIO
    0.86
    dafx
    0.85
    bibfield
    0.85
    %$$
    0.84
    Activations Density 2.327%

    No Known Activations