© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 3288
    Prev
    Next
    INDEX
    Explanations

    grade/level

    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
     পাকিস্তানে
    0.37
    עות
    0.37
     {}>,
    0.36
     weighting
    0.34
     hoo
    0.34
    osia
    0.34
     Jop
    0.34
     बजाज
    0.33
     вече
    0.33
    '/
    0.32
    POSITIVE LOGITS
     level
    1.09
     nivel
    1.02
     nível
    0.96
    level
    0.95
     niveau
    0.92
     LEVEL
    0.91
     Level
    0.90
    Level
    0.89
    レベル
    0.84
     niveaux
    0.84
    Activations Density 0.102%

    No Known Activations