© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 11674
    Prev
    Next
    INDEX
    Explanations

    torch library code

    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_40_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
    idase
    0.43
    ensee
    0.43
    𝐡
    0.41
    ObjectTemp
    0.39
    Url
    0.37
    дания
    0.37
     unidade
    0.37
    Kel
    0.37
     والدہ
    0.35
     unidad
    0.35
    POSITIVE LOGITS
     난
    0.39
    狹
    0.37
    난
    0.35
    ຂ
    0.34
    跨
    0.34
     закры
    0.34
    交叉
    0.34
     atraves
    0.33
    烫
    0.33
     sym
    0.33
    Activations Density 0.009%

    No Known Activations