© 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. 37196
    Prev
    Next
    INDEX
    Explanations

    these

    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
    s
    0.89
    ش
    0.82
    с
    0.82
    م
    0.78
    ید
    0.77
    ের
    0.76
    يل
    0.74
    기
    0.74
    áme
    0.73
    ne
    0.72
    POSITIVE LOGITS
    i
    1.23
    I
    0.97
    a
    0.84
    o
    0.84
    at
    0.78
    ,”
    0.77
    ,
    0.77
    !”
    0.77
    ’
    0.77
    ?”
    0.75
    Activations Density 0.023%

    No Known Activations