© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 176118
    Prev
    Next
    INDEX
    Explanations

    from a builder

    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_24_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
    Ī
    0.44
     وړیا
    0.43
    glieder
    0.42
    面积
    0.42
    D
    0.41
    学習
    0.41
    bara
    0.39
    ская
    0.38
     学習
    0.38
    عر
    0.37
    POSITIVE LOGITS
     Salim
    0.39
     apprezz
    0.39
    ပါ။
    0.38
     llamados
    0.37
     pname
    0.36
    搆
    0.35
     filos
    0.34
    গ্রেস
    0.34
     кла
    0.34
     Ape
    0.34
    Activations Density 0.000%

    No Known Activations