© 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. 112641
    Prev
    Next
    INDEX
    Explanations

    bù

    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
    at
    1.13
    I
    1.08
    ’’
    0.90
     että
    0.88
     that
    0.86
     kepada
    0.86
    Y
    0.80
    IN
    0.79
    atip
    0.79
     at
    0.78
    POSITIVE LOGITS
    ח
    1.19
    א
    1.16
    ли
    1.09
    ن
    1.06
    s
    1.05
    д
    1.05
    ,
    1.00
    ле
    0.99
    يا
    0.97
    স
    0.96
    Activations Density 0.002%

    No Known Activations