© 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. 12253
    Prev
    Next
    INDEX
    Explanations

    language related to special education and disabilities

    oai_token-act-pair · gemini-2.0-flash

    disabilities

    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
     nakalista
    -0.93
    IntoConstraints
    -0.81
     Disability
    -0.70
     disability
    -0.69
    PRNewswire
    -0.68
    InjectAttribute
    -0.65
     Handicapped
    -0.63
     handicapped
    -0.59
    Disability
    -0.59
     autism
    -0.58
    POSITIVE LOGITS
     specials
    0.55
    dis
    0.54
     Puerta
    0.52
    WebControls
    0.52
     estekak
    0.51
    Nail
    0.51
     Specials
    0.50
     Down
    0.50
    UIControlState
    0.50
    wiad
    0.48
    Activations Density 2.256%

    No Known Activations