© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 508
    Prev
    Next
    INDEX
    Explanations

    words indicating a certification

    oai_token-act-pair · gemini-2.0-flash

    certified

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    LookAnd
    -0.67
    DrawerToggle
    -0.62
    lapsingToolbar
    -0.62
     }}}
    -0.61
    parsedMessage
    -0.59
     ModelExpression
    -0.59
    !*\
    -0.59
     Paglinawan
    -0.57
     الرياضيه
    -0.57
    =$?
    -0.57
    POSITIVE LOGITS
    astify
    0.56
     acred
    0.49
     onOptions
    0.48
    pendicular
    0.47
    Vaata
    0.45
    hankelijk
    0.44
     chi̍t
    0.43
    dumps
    0.43
    DataAnnotations
    0.42
    pania
    0.42
    Activations Density 0.036%

    No Known Activations