© 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. 59160
    Prev
    Next
    INDEX
    Explanations

    decision, decline, accelerate, estimate

    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
     has
    1.19
    ers
    1.06
    x
    1.03
    ;
    1.01
    6
    0.98
    </strong>
    0.96
    es
    0.95
    and
    0.94
    ors
    0.93
    ans
    0.93
    POSITIVE LOGITS
    the
    1.31
    It
    0.97
    vē
    0.97
     for
    0.91
    น
    0.90
    mē
    0.88
    de
    0.87
     มัน
    0.86
    duğ
    0.86
    te
    0.85
    Activations Density 0.002%

    No Known Activations