© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 46336
    Prev
    Next
    INDEX
    Explanations

    app for

    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_3_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
    い
    0.89
    ব
    0.80
     .
    0.70
    માં
    0.68
    ል
    0.66
    ب
    0.66
    ט
    0.65
    ದ
    0.64
    กัน
    0.64
    ज
    0.64
    POSITIVE LOGITS
    ۰
    0.86
    re
    0.76
     Flows
    0.71
     Sloven
    0.63
    to
    0.63
     Copies
    0.59
    ANE
    0.59
    ोबर
    0.59
    lo
    0.59
    elah
    0.59
    Activations Density 0.002%

    No Known Activations