© 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. 5840
    Prev
    Next
    INDEX
    Explanations

    words related to political elections, leaders, and transitions of power.

    oai_token-act-pair · gemini-2.0-flash

    say [titles]

    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
     Boss
    -1.20
     Chief
    -1.16
    Boss
    -1.15
     Professor
    -1.13
    Professor
    -1.13
    Mayor
    -1.13
     boss
    -1.12
     CEO
    -1.11
     Mayor
    -1.11
    Chief
    -1.10
    POSITIVE LOGITS
     InputDecoration
    0.57
     propOrder
    0.51
     Wicidata
    0.51
    новништво
    0.50
    schild
    0.47
     NAL
    0.47
     Paglinawan
    0.44
    цездатний
    0.43
    gares
    0.43
    Cuántos
    0.43
    Activations Density 2.319%

    No Known Activations