© 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. 83536
    Prev
    Next
    INDEX
    Explanations

    chi ama

    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
     to
    1.59
    </h3>
    1.32
    ۰
    1.32
    UZ
    1.27
    UT
    1.26
    US
    1.18
    KeyDown
    1.17
     ול
    1.16
    YN
    1.15
    AL
    1.13
    POSITIVE LOGITS
    ت
    2.63
    ن
    2.55
    n
    2.36
    et
    2.31
    es
    2.22
    o
    2.19
    an
    2.17
    ان
    2.09
    os
    2.06
    न
    2.05
    Activations Density 0.000%

    No Known Activations