© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 252723
    Prev
    Next
    INDEX
    Explanations

    Cour

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    s
    0.56
    Ty
    0.44
    թ
    0.43
    planning
    0.42
    ﺖ
    0.41
    Mod
    0.40
    ట్‌
    0.40
     अन्याय
    0.40
    ی
    0.39
    TY
    0.39
    POSITIVE LOGITS
     dick
    0.42
     scrubber
    0.38
    浏
    0.36
    审美
    0.36
     COT
    0.35
     annot
    0.35
     Wiggins
    0.35
    erit
    0.35
    বাবু
    0.34
     widz
    0.34
    Activations Density 0.000%

    No Known Activations