© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 4942
    Prev
    Next
    INDEX
    Explanations

    code blocks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_3_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
    म
    2.83
    gies
    2.63
    ر
    2.57
    ب
    2.54
     lectura
    2.51
    га
    2.49
     amateurs
    2.46
    ehir
    2.43
     reckoning
    2.42
     deven
    2.39
    POSITIVE LOGITS
    Substituting
    2.97
    λί
    2.39
     eens
    2.34
    Με
    2.34
    ق
    2.32
    urious
    2.30
    జు
    2.29
     गार्ड
    2.29
    NONE
    2.25
    何
    2.23
    Activations Density 0.023%

    No Known Activations