© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 201942
    Prev
    Next
    INDEX
    Explanations

    sourdough starter

    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_6_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
    يا
    1.23
    كتب
    1.23
    ي
    1.22
    ם
    1.22
    ки
    1.15
    ذكر
    1.13
    كل
    1.11
    كس
    1.10
    കൾ
    1.08
    كار
    1.07
    POSITIVE LOGITS
    '
    1.07
    di
    1.03
    down
    1.02
    de
    0.89
    the
    0.88
    d
    0.88
    don
    0.87
    den
    0.86
    (
    0.84
    /
    0.84
    Activations Density 0.000%

    No Known Activations