© 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. 6188
    Prev
    Next
    INDEX
    Explanations

    words and phrases particularly related to Christian churches including dates, faith, meetings, and regular attendees

    oai_token-act-pair · gemini-2.0-flash

    technical or coded terms

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

    church and religion

    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
     snippetHide
    -0.52
    MENAFN
    -0.52
    oneofs
    -0.50
     관계
    -0.50
     lenker
    -0.50
     بيها
    -0.50
    onNext
    -0.48
    ValueStyle
    -0.48
     comb
    -0.47
    ctest
    -0.47
    POSITIVE LOGITS
    NOPQRST
    0.59
    +#+#
    0.51
     soins
    0.50
    rungsseite
    0.50
    parsedMessage
    0.47
    rrggbb
    0.47
    messageInfo
    0.47
     ministry
    0.47
    hoeddwyd
    0.47
    oa̍t
    0.47
    Activations Density 1.881%

    No Known Activations