© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 104903
    Prev
    Next
    INDEX
    Explanations

    CIA

    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
    ushi
    0.38
    Г
    0.37
    వో
    0.37
     pow
    0.35
    пону
    0.35
     ডো
    0.35
    dare
    0.34
    Τ
    0.34
    PO
    0.34
     Nih
    0.34
    POSITIVE LOGITS
     مزاح
    0.37
    னுடைய
    0.36
    CipherText
    0.36
     Carrick
    0.36
     ছল
    0.35
     gf
    0.34
     वचन
    0.34
     бар
    0.34
    配列
    0.34
     towarz
    0.33
    Activations Density 0.000%

    No Known Activations