© 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. 220813
    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
    ☼
    0.42
    NumConst
    0.41
     Questionnaire
    0.39
     রবি
    0.38
     Νο
    0.38
     Timurtaş
    0.37
     corto
    0.36
     boar
    0.35
     Wur
    0.35
    قامة
    0.35
    POSITIVE LOGITS
     đầy
    0.36
    oddsidemargin
    0.36
     dividend
    0.36
    უტ
    0.36
    ວ
    0.36
    ਟ
    0.36
     gehören
    0.36
    పూర్
    0.36
    Kerala
    0.35
    カス
    0.35
    Activations Density 0.000%

    No Known Activations