© 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. 12473
    Prev
    Next
    INDEX
    Explanations

    my spirit animal

    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
    ']['
    0.25
     केलेले
    0.25
     Einrichtungen
    0.24
     !}\
    0.24
     دماغ
    0.23
    秚
    0.23
     endExpNow
    0.23
     желу
    0.23
     penyakit
    0.23
    왑
    0.22
    POSITIVE LOGITS
     slogans
    0.28
     slogan
    0.27
    Indigenous
    0.26
     Indigenous
    0.26
     cudd
    0.24
     Pat
    0.24
    Pat
    0.23
    Doctor
    0.23
    Def
    0.22
    やら
    0.22
    Activations Density 0.001%

    No Known Activations