© 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. 143210
    Prev
    Next
    INDEX
    Explanations

    unrest, recommissioning, sets, wheeled, calmly, gliding

    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
    ли
    1.70
    ों
    1.53
    ৮
    1.53
    ם
    1.47
    ς
    1.45
    s
    1.43
    ের
    1.38
    ।
    1.37
    ים
    1.33
    ل
    1.33
    POSITIVE LOGITS
    و
    1.27
    า
    1.16
    EST
    1.16
    time
    1.15
    ａ
    1.14
    ం
    1.13
     a
    1.12
    お店
    1.12
    ção
    1.05
    ils
    1.05
    Activations Density 0.000%

    No Known Activations