© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 221542
    Prev
    Next
    INDEX
    Explanations

    actor

    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_10_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
    ر
    0.84
    ب
    0.81
    ut
    0.73
    rs
    0.66
    ᄍ
    0.63
    د
    0.63
    ม
    0.63
     aswell
    0.62
    rp
    0.61
    ல
    0.61
    POSITIVE LOGITS
    ן
    0.70
    anju
    0.68
     马
    0.67
     място
    0.66
     pię
    0.65
    }$,
    0.65
     },
    0.64
     Verhalten
    0.64
     メール
    0.64
     gebruiken
    0.63
    Activations Density 0.001%

    No Known Activations