© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5691
    Prev
    Next
    INDEX
    Explanations

    citations and question prompts

    oai_token-act-pair · gemini-2.0-flash

    non-English or encoded words

    np_token-act-pair-logits · gpt-4o-mini

    say "9"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     V
    -0.52
     D
    -0.52
     (
    -0.52
     T
    -0.50
    oso
    -0.49
     
    -0.49
     B
    -0.49
    X
    -0.48
    V
    -0.48
     P
    -0.47
    POSITIVE LOGITS
    aarrggbb
    1.20
     виправивши
    1.17
    expandindo
    1.14
    parsedMessage
    1.10
     estekak
    1.08
    InjectAttribute
    1.08
     tartalomajánló
    1.06
     مشين
    1.03
     متعلقه
    1.02
    IntoConstraints
    1.01
    Activations Density 11.422%

    No Known Activations