© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 195072
    Prev
    Next
    INDEX
    Explanations

    placeholder target variable `$@`

    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_15_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
    يف
    0.57
    وان
    0.56
    보기
    0.54
    ד
    0.54
    пет
    0.53
    葆
    0.52
    бы
    0.52
    وز
    0.52
    효
    0.52
    ويل
    0.51
    POSITIVE LOGITS
     ditth
    0.63
     inhomogeneities
    0.54
     विशिष्ट
    0.53
    fdPar
    0.52
     Tokugawa
    0.51
    jalpha
    0.50
     ω
    0.50
     thân
    0.49
     ellipsoid
    0.49
     appr
    0.49
    Activations Density 0.000%

    No Known Activations