© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 167755
    Prev
    Next
    INDEX
    Explanations

    she

    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_31_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
    完
    0.31
    闕
    0.31
    erad
    0.30
     arranc
    0.30
     լ
    0.30
     مقام
    0.30
    𝙊
    0.30
    uole
    0.29
     annen
    0.29
    磬
    0.29
    POSITIVE LOGITS
    umbu
    0.39
     saw
    0.36
     scarcely
    0.35
    CRETE
    0.35
     Saw
    0.35
     SAW
    0.35
    +...+
    0.34
     occupies
    0.33
    ༞
    0.32
     easily
    0.32
    Activations Density 0.006%

    No Known Activations