© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 237980
    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_32_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
    orption
    0.39
    기관
    0.39
     сделали
    0.38
    itley
    0.37
    运作
    0.37
    運営
    0.37
    liches
    0.36
    郅
    0.36
    マト
    0.35
     уровне
    0.35
    POSITIVE LOGITS
     Tam
    0.40
    તમ
    0.38
     mulig
    0.38
     Endgame
    0.37
     overweight
    0.37
     naszych
    0.36
    temp
    0.35
     cousin
    0.35
     Impossible
    0.35
     Possible
    0.35
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.