© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 182161
    Prev
    Next
    INDEX
    Explanations

    intermediate to advanced skill levels

    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_29_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
     harmless
    0.32
     권
    0.28
     Telling
    0.28
     безо
    0.28
     grains
    0.28
     kuni
    0.28
    巨大的
    0.27
     pote
    0.27
    🥶
    0.27
     haloes
    0.27
    POSITIVE LOGITS
     본격
    0.35
     läng
    0.32
    本格
    0.32
     tougher
    0.31
     längre
    0.31
    进来
    0.31
     harder
    0.30
     læng
    0.30
     toddler
    0.30
     مرحله
    0.30
    Activations Density 0.051%

    No Known Activations