© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 50569
    Prev
    Next
    INDEX
    Explanations

    testing keywords and punctuation

    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_10_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
     curviliné
    0.62
     тесто
    0.59
     જેના
    0.58
    ,
    0.57
    ’
    0.56
     médias
    0.54
     chemins
    0.53
     coche
    0.52
     pubescence
    0.52
     જેમાં
    0.52
    POSITIVE LOGITS
    G
    0.74
    M
    0.64
     ?”
    0.60
    od
    0.59
    L
    0.58
    ect
    0.57
    D
    0.57
    og
    0.55
    çok
    0.55
    aj
    0.54
    Activations Density 0.001%

    No Known Activations