© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 205881
    Prev
    Next
    INDEX
    Explanations

    Oracle database errors and keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_37_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
     décidé
    0.42
     doves
    0.40
     impre
    0.39
     bleaching
    0.39
    ەکە
    0.39
     decide
    0.38
     폴
    0.38
    homework
    0.38
     Cinta
    0.38
     décide
    0.38
    POSITIVE LOGITS
     SAP
    0.69
    SAP
    0.68
    Sap
    0.58
     sap
    0.57
     Sap
    0.50
    sap
    0.48
     HANA
    0.41
    urrences
    0.38
    𝗸
    0.38
    ^{*}$-
    0.38
    Activations Density 0.003%

    No Known Activations