© 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. 33018
    Prev
    Next
    INDEX
    Explanations

    A

    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
     tunes
    0.42
    IST
    0.42
     bist
    0.42
    ⁂
    0.41
    ISTAN
    0.41
     Tunes
    0.41
    ist
    0.41
    isses
    0.40
     Bist
    0.39
    bou
    0.39
    POSITIVE LOGITS
    бра
    0.50
     Ха
    0.48
    ブラ
    0.44
     Bras
    0.43
    Ха
    0.42
     ब्रा
    0.41
    rak
    0.41
     бра
    0.40
    ハ
    0.40
     MLA
    0.40
    Activations Density 0.002%

    No Known Activations