© 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. 54129
    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
    SEQU
    0.38
     Perak
    0.38
     HVAC
    0.37
    విద్య
    0.37
    riz
    0.37
     กรณี
    0.37
    ဉ
    0.37
    抔
    0.37
     receiving
    0.36
     sadly
    0.36
    POSITIVE LOGITS
    ⌝
    0.43
    gramModel
    0.37
     편집
    0.36
    ὥ
    0.36
     عش
    0.35
    future
    0.35
     movingRect
    0.34
    在这
    0.34
    থাৎ
    0.33
     паралле
    0.33
    Activations Density 0.000%

    No Known Activations