© 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. 8947
    Prev
    Next
    INDEX
    Explanations

    words about politics and politicians

    oai_token-act-pair · gemini-2.0-flash

    political criticism

    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
    Bronnen
    -0.69
     []).
    -0.57
    poel
    -0.56
    pona
    -0.54
    '])->
    -0.53
    Beijo
    -0.52
    ()])
    -0.52
    AsUp
    -0.52
    HttpFoundation
    -0.51
    MENAFN
    -0.51
    POSITIVE LOGITS
     sho
    0.78
    PHONY
    0.63
     gul
    0.63
     cra
    0.63
     pand
    0.62
    ConstraintMaker
    0.61
    хьтан
    0.60
     bung
    0.59
     bot
    0.58
    fla
    0.58
    Activations Density 8.304%

    No Known Activations