© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 158611
    Prev
    Next
    INDEX
    Explanations

    portray

    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_50_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
     oo
    0.48
     clas
    0.46
     ക്ലാ
    0.44
     y
    0.42
    jf
    0.42
     wf
    0.41
     Duff
    0.41
     deferred
    0.41
     clf
    0.41
     dune
    0.39
    POSITIVE LOGITS
    ≧
    0.40
    ندگی
    0.38
    ifar
    0.38
    Roi
    0.37
    KOM
    0.37
    ERI
    0.36
    isserie
    0.36
    iotic
    0.36
    يتي
    0.36
    ضم
    0.35
    Activations Density 0.001%

    No Known Activations