© 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. 3975
    Prev
    Next
    INDEX
    Explanations

    mentions of conflict in specific geographic regions.

    oai_token-act-pair · gemini-2.0-flash

    wars and conflicts

    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
     Coyle
    -0.57
     commerciales
    -0.53
    consulté
    -0.51
     cappello
    -0.50
    Singing
    -0.49
    Dating
    -0.49
     meditación
    -0.48
     médicaux
    -0.48
     orologio
    -0.48
    Formulation
    -0.48
    POSITIVE LOGITS
     IndexPath
    0.62
    msgSender
    0.59
    tangentMode
    0.58
     Roskov
    0.57
    bewerken
    0.57
     autorytatywna
    0.56
    Дереккөздер
    0.55
    setVerticalGroup
    0.55
    RenderAtEndOf
    0.55
     iconLine
    0.55
    Activations Density 8.436%

    No Known Activations