© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 61293
    Prev
    Next
    INDEX
    Explanations

    listing things

    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_2_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
    一
    1.59
    .
    1.35
    leri
    1.26
    leigh
    1.19
    ৫
    1.13
    la
    1.09
    .\
    1.09
    лер
    1.09
    lerinde
    1.09
    ۴
    1.07
    POSITIVE LOGITS
     to
    1.76
    '
    1.59
    ס
    1.45
    of
    1.27
    ן
    1.25
    م
    1.22
    น
    1.18
    ิ
    1.13
    A
    1.10
    อ
    1.10
    Activations Density 0.002%

    No Known Activations