© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 14771
    Prev
    Next
    INDEX
    Explanations

    apk and Educators

    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_13_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
    ix
    0.12
    in
    0.11
    ון
    0.11
    icot
    0.10
    *\*
    0.10
    ib
    0.10
    ino
    0.10
    pp
    0.10
    ின
    0.10
    F
    0.10
    POSITIVE LOGITS
     تشوف
    0.12
    heatmap
    0.11
    temperatur
    0.11
    blockSize
    0.10
     உள்ளன
    0.10
    για
    0.10
     glimpse
    0.10
    pouring
    0.10
     गरजेचे
    0.10
    different
    0.10
    Activations Density 0.007%

    No Known Activations