© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 171633
    Prev
    Next
    INDEX
    Explanations

    authors and titles

    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_20_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
     cashew
    0.43
     darken
    0.42
    тых
    0.42
     premature
    0.40
    ῆ
    0.40
    煥
    0.40
    ろん
    0.39
    windowFixedWidth
    0.39
    Gosudarstvennyj
    0.38
     callus
    0.38
    POSITIVE LOGITS
     &
    0.45
     seves
    0.45
     Extremely
    0.43
    Quand
    0.42
    감
    0.42
     इंपॉर्ट
    0.41
     comm
    0.40
     quand
    0.40
    ১
    0.40
     víct
    0.39
    Activations Density 0.000%

    No Known Activations