© 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. 49978
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    은
    0.65
     군
    0.62
    ದ
    0.62
     सैन्य
    0.62
    ख
    0.60
    계
    0.60
    де
    0.59
    ка
    0.59
    이
    0.58
     कु
    0.58
    POSITIVE LOGITS
     einzelnen
    0.64
    త్మిక
    0.63
     jib
    0.61
    ান্ডের
    0.57
     sprechen
    0.56
     anderen
    0.54
     einzige
    0.54
     puissiez
    0.54
     einzelne
    0.54
     同时
    0.54
    Activations Density 0.000%

    No Known Activations