© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 159103
    Prev
    Next
    INDEX
    Explanations

    model

    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_50_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
    口碑
    0.37
     funkcjon
    0.37
    ញ
    0.37
    صوص
    0.36
    rpart
    0.36
     dam
    0.36
     amusement
    0.36
     নির্ব
    0.36
     Amar
    0.36
    AAAAAAAA
    0.36
    POSITIVE LOGITS
     Blue
    0.40
     thes
    0.38
     dide
    0.37
     青
    0.37
    Prog
    0.37
    elig
    0.37
    prog
    0.37
     १२
    0.37
     Hate
    0.36
    BLUE
    0.36
    Activations Density 0.005%

    No Known Activations