© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 202591
    Prev
    Next
    INDEX
    Explanations

    numbers and technical terms

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
     Cob
    0.40
    Cob
    0.39
    목
    0.39
    Tom
    0.38
    需要在
    0.38
    ൃ
    0.38
     krim
    0.37
     tendre
    0.37
    係
    0.37
     কমল
    0.37
    POSITIVE LOGITS
     значения
    0.41
     Исто
    0.40
     Vent
    0.39
    yección
    0.38
    junctive
    0.38
     सिक्स
    0.37
    HANDLER
    0.37
     pca
    0.37
     Btn
    0.37
     ஆறு
    0.37
    Activations Density 0.004%

    No Known Activations