© 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. 84404
    Prev
    Next
    INDEX
    Explanations

    lose data or power

    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
    ס
    1.84
    1
    1.59
    ش
    1.58
    is
    1.53
    ስ
    1.51
    도
    1.48
    ال
    1.46
    ח
    1.45
    وی
    1.42
    ש
    1.41
    POSITIVE LOGITS
    .
    1.90
    o
    1.66
    -
    1.43
     on
    1.41
    z
    1.38
    e
    1.35
    er
    1.34
    ↵
    1.23
    ar
    1.19
    ches
    1.16
    Activations Density 0.002%

    No Known Activations