© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 8106
    Prev
    Next
    INDEX
    Explanations

    URLs and related website names

    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_40_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
    Som
    0.27
    खास्त
    0.24
    Elapsed
    0.24
     अला
    0.22
    くら
    0.22
    Pages
    0.22
    Central
    0.22
    =""><
    0.21
     Som
    0.21
     Tool
    0.21
    POSITIVE LOGITS
     शुक्
    0.27
     ))->
    0.27
    patx
    0.26
    駋
    0.26
     COc
    0.25
     melts
    0.25
    zący
    0.25
    ayo
    0.25
     mata
    0.25
     پید
    0.25
    Activations Density 0.002%

    No Known Activations