© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 34-GEMMASCOPE-2-TRANSCODER-262K
    4. 15947
    Prev
    Next
    INDEX
    Explanations

    column vector

    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_34_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
    WITT
    0.40
    REPEAT
    0.38
    ền
    0.37
    铺
    0.37
     blankets
    0.36
     повторя
    0.36
     повто
    0.36
    盆
    0.36
     repeat
    0.36
    宽
    0.36
    POSITIVE LOGITS
     tall
    1.06
     vertical
    0.98
     verticales
    0.96
     вертика
    0.95
     vertically
    0.93
    Vertical
    0.92
     upright
    0.91
     Vertical
    0.91
     Tall
    0.90
    Tall
    0.89
    Activations Density 0.111%

    No Known Activations