© 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
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 125053
    Prev
    Next
    INDEX
    Explanations

    row-major vector echelon form

    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_3_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
    ן
    0.74
    わざ
    0.68
     dramatically
    0.64
     conceivably
    0.64
    ORE
    0.64
     not
    0.62
     volupt
    0.61
     depolar
    0.61
    d
    0.61
    (+
    0.59
    POSITIVE LOGITS
    ть
    0.63
    1
    0.63
    2
    0.62
    4
    0.62
    ны
    0.60
    ки
    0.59
    मा
    0.57
    利亚
    0.57
     }
    0.57
    ust
    0.57
    Activations Density 0.001%

    No Known Activations