© 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. 116831
    Prev
    Next
    INDEX
    Explanations

    within sentences or content

    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
    apä
    0.43
    heits
    0.39
    angkah
    0.37
    蛲
    0.37
    świad
    0.36
     põh
    0.36
     दिखा
    0.35
    țul
    0.35
     atau
    0.35
    หรือ
    0.35
    POSITIVE LOGITS
     జాగ్ర
    0.35
    社
    0.33
    нинград
    0.33
     two
    0.33
     Keane
    0.33
     hurry
    0.32
     दोन
    0.32
     seller
    0.31
     Nem
    0.31
     savage
    0.31
    Activations Density 0.000%

    No Known Activations