© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 8460
    Prev
    Next
    INDEX
    Explanations

    references to political parties or groups of people affected by something

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     party
    -2.72
    Party
    -2.56
    party
    -2.52
     Party
    -2.52
     PARTY
    -2.41
    PARTY
    -2.22
     Parties
    -1.87
     parties
    -1.84
    parties
    -1.73
    Parties
    -1.73
    POSITIVE LOGITS
     ujednoznacz
    0.63
     kasarigan
    0.56
    InputBorder
    0.55
    Hochspringen
    0.55
    ThroughAttribute
    0.54
     GenerationType
    0.52
     <<<<<<<<<<<<<<
    0.51
    Források
    0.50
    RectangleBorder
    0.50
    cinogenicity
    0.50
    Activations Density 1.250%

    No Known Activations