© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 9490
    Prev
    Next
    INDEX
    Explanations

    l

    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
     kapcsol
    0.79
    &
    0.77
    asih
    0.70
     definição
    0.69
    $&
    0.67
     بج
    0.66
     defined
    0.65
    ほと
    0.65
     surrounds
    0.65
     lexical
    0.64
    POSITIVE LOGITS
    щихся
    0.73
     RTR
    0.67
    }());
    0.65
     PHIL
    0.63
    璃
    0.63
    TR
    0.63
    PHIL
    0.62
     மண
    0.62
    𝚁
    0.62
    偻
    0.62
    Activations Density 0.001%

    No Known Activations