© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 205476
    Prev
    Next
    INDEX
    Explanations

    segmentation or sequence beginnings

    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_37_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
     nawet
    0.44
    ໃ
    0.44
    adil
    0.41
     kneeling
    0.37
    Tov
    0.37
     diagonalization
    0.37
     filth
    0.36
    튬
    0.36
     programming
    0.36
    breakable
    0.35
    POSITIVE LOGITS
     Arbeits
    0.38
     berichtet
    0.38
     Hellen
    0.37
    代谢
    0.36
    店頭
    0.36
     अक्ष
    0.36
    orschungs
    0.35
     sits
    0.35
    焦
    0.34
     tester
    0.34
    Activations Density 0.001%

    No Known Activations