© 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. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 66732
    Prev
    Next
    INDEX
    Explanations

    celebrity names

    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_41_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
     Loksatta
    0.48
    午後
    0.43
     desag
    0.40
    Five
    0.38
     bis
    0.38
     пя
    0.37
     বিকেল
    0.37
    ₅
    0.37
    BIS
    0.36
    ૫
    0.36
    POSITIVE LOGITS
     Gent
    0.43
    घु
    0.40
     gentleman
    0.40
     Carta
    0.40
     Mek
    0.39
    urate
    0.38
    gez
    0.38
     sv
    0.38
     কানে
    0.37
     transported
    0.37
    Activations Density 0.004%

    No Known Activations