© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 92204
    Prev
    Next
    INDEX
    Explanations

    without its

    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_11_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
    t
    0.96
    n
    0.88
    et
    0.87
    ag
    0.86
    im
    0.77
    er
    0.74
    il
    0.74
    al
    0.74
    e
    0.72
    aq
    0.72
    POSITIVE LOGITS
     tanggal
    0.64
    Date
    0.57
    ц
    0.57
    Is
    0.55
    Face
    0.54
     kuitenkin
    0.54
     शु
    0.54
    Farmers
    0.54
    Due
    0.53
     aikana
    0.53
    Activations Density 0.005%

    No Known Activations