© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 79923
    Prev
    Next
    INDEX
    Explanations

    bull variations

    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
    '
    2.47
    ession
    1.36
    ’
    1.27
    '،
    1.26
    ING
    1.20
    ()'
    1.18
    ﺭ
    1.17
    O
    1.16
    antal
    1.11
    ract
    1.10
    POSITIVE LOGITS
    ل
    2.66
    و
    2.22
    다
    2.14
    ת
    2.13
    л
    2.02
    ל
    1.79
    ت
    1.67
    로
    1.60
    ल
    1.57
    ル
    1.55
    Activations Density 0.000%

    No Known Activations