© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 107607
    Prev
    Next
    INDEX
    Explanations

    everything or nothing

    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_1_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
    s
    1.70
    י
    1.69
    ו
    1.54
    د
    1.52
    ب
    1.47
    ی
    1.45
    ב
    1.45
    ר
    1.39
    ي
    1.30
    I
    1.28
    POSITIVE LOGITS
    ang
    1.20
    ى
    1.19
    ay
    1.06
    ess
    1.04
    RO
    0.95
    ier
    0.94
    ный
    0.91
    gång
    0.91
    é
    0.89
    azing
    0.89
    Activations Density 0.000%

    No Known Activations