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

    Neuronpedia

    Jacobian LensNEW
    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. 43438
    Prev
    Next
    INDEX
    Explanations

    setting axis labels

    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
    I
    1.37
    ne
    0.97
     in
    0.93
    (
    0.91
    在
    0.80
    na
    0.80
     I
    0.71
    A
    0.70
    Ii
    0.69
    O
    0.68
    POSITIVE LOGITS
    ார்
    0.79
    емой
    0.77
    as
    0.76
    ashed
    0.73
    тит
    0.72
    ைக்கு
    0.71
    uje
    0.70
    ᱐
    0.70
    োর
    0.66
     форму
    0.66
    Activations Density 0.003%

    No Known Activations