© 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. 3722
    Prev
    Next
    INDEX
    Explanations

    named members of the US government and associated political institutions

    oai_token-act-pair · gemini-2.0-flash

    Period

    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
     Representatives
    -0.75
     senator
    -0.74
     Republican
    -0.74
     Democratic
    -0.72
    Lähteet
    -0.68
     Democrat
    -0.66
     senators
    -0.66
     مرئيه
    -0.63
     congressman
    -0.63
     &___
    -0.61
    POSITIVE LOGITS
     المعيارى
    0.60
     tratto
    0.57
     TERM
    0.48
     Allociné
    0.47
     vux
    0.44
     realizzare
    0.44
     uscire
    0.44
     lined
    0.44
     cavalli
    0.44
    QUID
    0.43
    Activations Density 11.877%

    No Known Activations