© 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. 125986
    Prev
    Next
    INDEX
    Explanations

    endless possibilities

    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
    ’
    1.15
    ak
    0.93
    il
    0.76
    ?:
    0.72
    ק
    0.70
    '
    0.67
     for
    0.66
    G
    0.64
    ib
    0.61
    ore
    0.61
    POSITIVE LOGITS
    )。
    0.84
    ）。
    0.80
    ský
    0.68
     Италии
    0.68
    聞いた
    0.66
    backgroundSplit
    0.66
    地区的
    0.65
    کش
    0.64
    .。
    0.64
    "。
    0.64
    Activations Density 0.000%

    No Known Activations