© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 205501
    Prev
    Next
    INDEX
    Explanations

    French places

    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_56_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
     ch
    2.69
     च
    1.55
     Ch
    1.55
    Ch
    1.54
     چ
    1.38
     চ
    1.34
    ch
    1.19
     ч
    1.17
    ช
    1.10
     ши
    1.04
    POSITIVE LOGITS
    මු
    0.36
    стях
    0.35
    Ļ
    0.35
    γων
    0.34
    ppin
    0.33
    稅
    0.33
     Taxes
    0.32
    πλ
    0.32
    凉
    0.32
    ্সা
    0.32
    Activations Density 0.001%

    No Known Activations