© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 14634
    Prev
    Next
    INDEX
    Explanations

    U.S. legal language related to taxes, employees, and individuals

    oai_token-act-pair · gemini-2.0-flash

    legal/bureaucratic contexts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    WindowConstants
    -0.60
    persons
    -0.57
    ukone
    -0.57
     persons
    -0.56
    Persons
    -0.50
     Persons
    -0.50
    retch
    -0.47
    NamedQueries
    -0.47
    }(),
    -0.46
     PERSONS
    -0.46
    POSITIVE LOGITS
    UnsafeEnabled
    0.67
     ModelExpression
    0.67
    ftagPool
    0.61
    isDirectory
    0.60
     onAnimation
    0.60
     ExecuteAsync
    0.58
    bkz
    0.57
     متعلقه
    0.57
    entait
    0.56
    easeOut
    0.55
    Activations Density 11.220%

    No Known Activations