© 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. 6730
    Prev
    Next
    INDEX
    Explanations

    words related to political or government figures and events

    oai_token-act-pair · gemini-2.0-flash

    news excerpts

    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
    urlpatterns
    -0.64
    ANTLR
    -0.60
     denial
    -0.60
     Drapeau
    -0.59
     defending
    -0.57
    INGHAM
    -0.57
     Denial
    -0.57
    GraphicsUnit
    -0.56
     Denison
    -0.56
     DEN
    -0.55
    POSITIVE LOGITS
    Tikang
    0.56
     متعلقه
    0.45
    cloudf
    0.45
    StartTag
    0.43
     MPC
    0.42
    lois
    0.42
    Msp
    0.42
     wikipagina
    0.40
    SearchView
    0.40
    Suggestion
    0.40
    Activations Density 13.673%

    No Known Activations