© 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. 12025
    Prev
    Next
    INDEX
    Explanations

    mentions of dates, numbers, locations, names, laws, or studies

    oai_token-act-pair · gemini-2.0-flash

    broad, unrelated text

    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
     it
    -0.74
    EndProject
    -0.66
    XmlAccessorType
    -0.64
     transfieras
    -0.60
    EndContext
    -0.60
     незавершена
    -0.60
    LookAnd
    -0.59
    AutoScaleMode
    -0.59
    each
    -0.58
    essentially
    -0.58
    POSITIVE LOGITS
     émissions
    0.60
     Manipur
    0.60
     للمعارف
    0.56
     buckwheat
    0.56
     Tacitus
    0.55
     Carmelo
    0.55
     Constitucional
    0.54
     églises
    0.53
     boî
    0.53
     disturbed
    0.53
    Activations Density 19.951%

    No Known Activations