© 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-3-4B-IT
    5. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 9326
    Prev
    Next
    INDEX
    Explanations

    mathematical sets

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_25_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    宀
    0.70
     Ac
    0.64
     estrat
    0.64
     Care
    0.63
     ketiga
    0.63
     Dik
    0.63
     Great
    0.63
     caffè
    0.63
     GitHub
    0.62
     []*
    0.62
    POSITIVE LOGITS
     proposing
    0.96
     proposed
    0.91
    Proposed
    0.88
     proposes
    0.84
    proposed
    0.84
    Proposal
    0.83
     Proposed
    0.79
     exposing
    0.74
     propose
    0.70
     proposal
    0.69
    Activations Density 0.000%

    No Known Activations