© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 213759
    Prev
    Next
    INDEX
    Explanations

    routes and paths

    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
     enlighten
    0.40
    دخ
    0.36
    Bloom
    0.36
    jq
    0.36
    Ƌ
    0.35
     neuritis
    0.35
    mts
    0.35
    ̡
    0.35
    र्श
    0.34
    ukiy
    0.34
    POSITIVE LOGITS
     тра
    1.63
     tras
    1.30
     tra
    1.20
     trase
    1.09
    tras
    1.05
     Tra
    1.05
     Tras
    1.04
    Tras
    1.00
     traz
    0.99
    тра
    0.97
    Activations Density 0.000%

    No Known Activations