© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 35890
    Prev
    Next
    INDEX
    Explanations

    stylesheet href

    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_31_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
    ocols
    0.39
     رائے
    0.38
     touted
    0.38
     carefully
    0.37
     adap
    0.36
    кот
    0.36
     scrim
    0.36
    ^{\#}\
    0.36
     cc
    0.36
     Nh
    0.35
    POSITIVE LOGITS
    ীর
    0.37
     প্রাসাদ
    0.35
    रेशन
    0.35
     MAGIC
    0.35
     இணைந்து
    0.33
    枌
    0.33
     عبر
    0.33
    olta
    0.33
     सीड
    0.33
    Fert
    0.32
    Activations Density 0.001%

    No Known Activations