© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 53589
    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_31_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
     lineColor
    0.46
     الاسم
    0.43
    ດ້
    0.43
    WithName
    0.42
     personalmente
    0.41
    닮
    0.41
     delegado
    0.40
     이름
    0.40
    Sandra
    0.40
     नाम
    0.39
    POSITIVE LOGITS
     thỏa
    0.41
     predictable
    0.41
     antic
    0.38
     Eich
    0.38
    मैन
    0.35
     Eisenhower
    0.35
     predictability
    0.35
     cab
    0.35
     Predict
    0.35
     &
    0.35
    Activations Density 0.000%

    No Known Activations