© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 11835
    Prev
    Next
    INDEX
    Explanations

    words or phrases relating to legal events, politics, American football or well-known disasters

    oai_token-act-pair · gemini-2.0-flash

    legal troubles and trials

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     дописавши
    -0.84
    +#+#
    -0.67
     ModelExpression
    -0.63
    COUVER
    -0.59
    >",
    -0.59
     \%)
    -0.56
    RouterModule
    -0.56
     MainAxisSize
    -0.55
     ***!
    -0.55
     kasarigan
    -0.54
    POSITIVE LOGITS
    TProtocol
    0.61
     sauvages
    0.55
    рованные
    0.55
    рованных
    0.50
     Enth
    0.49
    AsUp
    0.48
    рованного
    0.48
    WarningLevel
    0.47
     atve
    0.46
     paesaggio
    0.46
    Activations Density 2.505%

    No Known Activations