© 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-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 124458
    Prev
    Next
    INDEX
    Explanations

    string slice

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-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
    of
    0.80
     (
    0.72
    e
    0.69
    ح
    0.66
    ן
    0.63
    什么
    0.61
    ation
    0.59
     of
    0.59
     where
    0.56
    opedic
    0.56
    POSITIVE LOGITS
    ين
    0.67
    )’
    0.66
    r
    0.64
    ид
    0.64
    ви
    0.61
    стойчи
    0.61
     incertid
    0.61
     kto
    0.59
     compétences
    0.59
    b
    0.59
    Activations Density 0.002%

    No Known Activations