© 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. 25683
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ｋ
    0.57
    ون
    0.53
     Fq
    0.49
    টি
    0.48
    থ
    0.48
    íte
    0.47
    িক্স
    0.47
    Ϫ
    0.47
    ान
    0.46
    ロー
    0.46
    POSITIVE LOGITS
    O
    0.56
     used
    0.50
     do
    0.46
     said
    0.46
    arken
    0.45
     gebruikt
    0.45
     over
    0.45
    结束
    0.44
     використову
    0.44
     metaphor
    0.43
    Activations Density 0.000%

    No Known Activations