© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 148822
    Prev
    Next
    INDEX
    Explanations

    help with use of

    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_23_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
    髄
    0.32
     材料
    0.31
     मटेरियल
    0.31
    idar
    0.30
     නිෂ්පා
    0.30
     Sustainability
    0.30
    ridge
    0.30
     pequenos
    0.30
     компен
    0.30
    abhuto
    0.29
    POSITIVE LOGITS
    "><
    0.34
    DATE
    0.32
     ಕೇಳ
    0.29
    不得不
    0.28
    道を
    0.28
     lorsque
    0.28
     DATE
    0.27
     limitation
    0.27
     मानना
    0.27
     तिथि
    0.27
    Activations Density 0.000%

    No Known Activations