© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 237879
    Prev
    Next
    INDEX
    Explanations

    file, accounts, cup, receptor, server, report, boards, notebook

    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_32_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
     Alvar
    0.38
     கூட்டு
    0.38
     Use
    0.38
     Lights
    0.37
     στους
    0.36
    া
    0.36
     På
    0.36
     Nä
    0.36
     ‎
    0.36
     Zh
    0.35
    POSITIVE LOGITS
    と思っています
    0.40
     находя
    0.36
     አንዳንድ
    0.36
     situé
    0.35
    صیٰ
    0.35
    embangkan
    0.35
     circunst
    0.35
     prosp
    0.34
    ELD
    0.34
     née
    0.34
    Activations Density 0.066%

    No Known Activations