© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 135057
    Prev
    Next
    INDEX
    Explanations

    shake, shook, shaken, shaking

    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_6_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
    ות
    1.16
     pouze
    1.11
     vozila
    1.09
    т
    1.07
    라인
    1.06
     entidad
    1.04
     rique
    1.04
     vode
    1.03
     okvir
    1.02
     prawie
    0.99
    POSITIVE LOGITS
    f
    1.43
    for
    1.30
    ik
    1.29
    k
    1.27
    an
    1.26
    ad
    1.26
    ir
    1.23
    ong
    1.23
    c
    1.23
    z
    1.23
    Activations Density 0.000%

    No Known Activations