© 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. 84003
    Prev
    Next
    INDEX
    Explanations

    prefix PRE followed by a word stem

    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
    л
    2.59
    ل
    1.97
    ল
    1.76
    ル
    1.74
    ם
    1.66
    ल
    1.57
    ל
    1.54
    лдуу
    1.52
    ர்ஸ்
    1.44
    سی
    1.39
    POSITIVE LOGITS
    ,
    1.86
    ed
    1.84
    ing
    1.77
    es
    1.70
    em
    1.65
    e
    1.55
    s
    1.48
    ad
    1.47
    im
    1.41
    am
    1.40
    Activations Density 0.000%

    No Known Activations