© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 142741
    Prev
    Next
    INDEX
    Explanations

    browsers

    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_0_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
    ру
    1.59
    يل
    1.38
    .。
    1.30
    ι
    1.26
    مان
    1.23
    ுகிற
    1.23
    ς
    1.18
    مة
    1.17
    nya
    1.16
    なる
    1.16
    POSITIVE LOGITS
    ↵
    1.86
    im
    1.85
    g
    1.84
    d
    1.83
    of
    1.80
    c
    1.73
    ii
    1.69
    ع
    1.68
    t
    1.66
    m
    1.66
    Activations Density 0.000%

    No Known Activations