© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 46685
    Prev
    Next
    INDEX
    Explanations

    more descriptive

    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
    ,
    0.95
    ä
    0.89
    ası
    0.75
    '}
    0.72
    ')
    0.70
    在于
    0.69
    RefManager
    0.67
    ästä
    0.67
     надеюсь
    0.66
     industria
    0.64
    POSITIVE LOGITS
    op
    0.68
    1
    0.68
    għ
    0.60
    g
    0.60
     C
    0.59
    IT
    0.58
     Тому
    0.57
     అంతే
    0.57
    int
    0.56
    div
    0.56
    Activations Density 0.019%

    No Known Activations