© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 102731
    Prev
    Next
    INDEX
    Explanations

    at/by prepositions

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_44_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
    าล
    0.38
    ToFile
    0.38
    征
    0.37
     ২০১৫
    0.36
    ยายาม
    0.36
    획
    0.36
     Calvert
    0.36
    ᕝ
    0.35
    orius
    0.35
     pored
    0.35
    POSITIVE LOGITS
     chez
    1.77
     bei
    1.68
     لدى
    1.51
     bij
    1.37
     عند
    1.36
     Bei
    1.31
    Chez
    1.31
     Chez
    1.27
     عنده
    1.26
     presso
    1.25
    Activations Density 0.017%

    No Known Activations