© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 23486
    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_56_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
     а
    0.67
    ア
    0.50
    a
    0.48
    𝑎
    0.47
    ａ
    0.47
     अ
    0.44
     a
    0.44
     ap
    0.42
    а
    0.42
     ა
    0.40
    POSITIVE LOGITS
     sub
    0.59
    sub
    0.58
     Sub
    0.57
    Sub
    0.56
     суб
    0.51
     SUB
    0.50
    getSub
    0.47
     subd
    0.44
     subfamily
    0.42
     right
    0.40
    Activations Density 0.000%

    No Known Activations