© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 194710
    Prev
    Next
    INDEX
    Explanations

    cloud

    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_27_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
     lawmakers
    0.38
    鋆
    0.36
     indicating
    0.35
     característica
    0.35
     FI
    0.35
     FIG
    0.34
     proceeding
    0.34
     Guarantee
    0.34
     म्हणूनच
    0.34
     ###
    0.33
    POSITIVE LOGITS
    ရား
    0.43
     buhay
    0.38
    дами
    0.38
     dilig
    0.37
     pued
    0.37
     sueños
    0.37
     dren
    0.37
     ured
    0.37
     alguna
    0.36
     estudios
    0.36
    Activations Density 0.000%

    No Known Activations