© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11810
    Prev
    Next
    INDEX
    Explanations

    words related to authority, headings, theories, visuals, and officialdom

    oai_token-act-pair · gemini-2.0-flash

    authorities

    np_max-act · gemini-2.0-flash

    say "space" Method used: 2 — because most following tokens start with a leading space, 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_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    <bos>
    -0.96
    Personensuche
    -0.62
    >*/
    -0.60
    '});
    -0.59
    MessageTagHelper
    -0.57
     tartalomajánló
    -0.57
    <h4>
    -0.55
     <=",
    -0.55
    GEBURTSDATUM
    -0.52
    ())->
    -0.51
    POSITIVE LOGITS
     pattes
    0.63
    satisfaction
    0.62
    ArgsConstructor
    0.62
    saraba
    0.60
    odule
    0.60
     econômica
    0.59
    逅
    0.59
    بینی
    0.59
    ligible
    0.59
     Sonny
    0.59
    Activations Density 1.332%

    No Known Activations