© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 12080
    Prev
    Next
    INDEX
    Explanations

    morning + star, Joe, Glory, calm, sickness

    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_40_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
     Supper
    0.41
    咖
    0.38
     профессии
    0.38
    isAdmin
    0.38
     isAdmin
    0.37
     clears
    0.37
    õi
    0.36
     وطن
    0.36
    psies
    0.35
    ㄶ
    0.35
    POSITIVE LOGITS
    察
    0.37
    hesi
    0.36
     peaked
    0.35
     sprouted
    0.35
    yr
    0.34
     LOUIS
    0.34
    traj
    0.34
    Cruz
    0.33
     Fontaine
    0.33
    MONT
    0.33
    Activations Density 0.000%

    No Known Activations