© 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. 32476
    Prev
    Next
    INDEX
    Explanations

    **FIRST** or origin

    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
    所
    0.41
     قص
    0.39
    烙
    0.38
     tit
    0.38
     kiu
    0.37
    tenberg
    0.37
    刄
    0.37
     RY
    0.36
    榕
    0.36
    ណា
    0.36
    POSITIVE LOGITS
     anh
    0.41
    ▓
    0.40
     eZ
    0.37
    ährt
    0.37
     అమ్మ
    0.36
     først
    0.36
     FIRST
    0.35
     prevails
    0.35
    trem
    0.35
    漉
    0.35
    Activations Density 0.015%

    No Known Activations