© 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. 493
    Prev
    Next
    INDEX
    Explanations

    words or phrases that connect different ideas, conditions or situations

    oai_token-act-pair · gemini-2.0-flash

    separation or connection

    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
     Efq
    -0.83
     Theſe
    -0.81
     myſelf
    -0.81
     himſelf
    -0.80
     Eſ
    -0.78
     whoſe
    -0.76
    Попис
    -0.75
     Diſ
    -0.73
     <=",
    -0.73
     itſelf
    -0.73
    POSITIVE LOGITS
    γμα
    0.50
    :+:
    0.45
     pure
    0.42
    tetur
    0.41
     trim
    0.40
     Mr
    0.40
     br
    0.39
    Literals
    0.39
    AllowAnonymous
    0.38
     M
    0.37
    Activations Density 3.064%

    No Known Activations