© 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. 59226
    Prev
    Next
    INDEX
    Explanations

    reinforcing stereotypes or cycles

    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
    '
    2.16
    i
    1.50
    a
    1.35
    ে
    1.31
    ië
    1.30
    ي
    1.27
    el
    1.25
    dı
    1.21
    -
    1.19
    ៩
    1.16
    POSITIVE LOGITS
    ש
    1.43
    お
    1.40
    ED
    1.37
    ش
    1.30
    ग
    1.24
    یت
    1.22
    กัน
    1.15
    ک
    1.13
    ला
    1.13
    ES
    1.13
    Activations Density 0.000%

    No Known Activations