© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 82426
    Prev
    Next
    INDEX
    Explanations

    AIDS

    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
    .
    2.20
    א
    1.59
    1
    1.56
    \
    1.49
    م
    1.46
     the
    1.45
    ا
    1.41
    os
    1.38
    ت
    1.38
    he
    1.38
    POSITIVE LOGITS
    л
    1.40
     convirtió
    1.34
     doua
    1.30
    to
    1.30
     as
    1.27
     tornou
    1.16
    ुभ
    1.15
    division
    1.12
    described
    1.09
    ल
    1.09
    Activations Density 0.000%

    No Known Activations