© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10195
    Prev
    Next
    INDEX
    Explanations

    words relating to legal precedings, awards or competitions.

    oai_token-act-pair · gemini-2.0-flash

    Presentations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    NameInMap
    -0.77
     GenerationType
    -0.75
    ReusableCell
    -0.74
     незавершена
    -0.73
    mtrl
    -0.63
    AxisAlignment
    -0.63
     ModelExpression
    -0.61
    Predecesor
    -0.60
    PMailer
    -0.58
     Wicidata
    -0.57
    POSITIVE LOGITS
     at
    2.55
    At
    1.38
     At
    1.38
     tại
    1.25
    at
    1.20
     	e
    0.90
     bei
    0.89
     ở
    0.83
     AT
    0.77
    앳
    0.75
    Activations Density 2.636%

    No Known Activations