© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 8821
    Prev
    Next
    INDEX
    Explanations

    plot arguments: title, color, location

    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
     звезд
    0.44
     SLASH
    0.42
    SLASH
    0.39
     spacers
    0.39
    ૯
    0.39
     имму
    0.39
     UNIV
    0.39
    ઋ
    0.38
     Sauce
    0.38
     ಸಂಖ್ಯ
    0.38
    POSITIVE LOGITS
     Kae
    0.40
     Kreuz
    0.38
     test
    0.38
     adh
    0.38
    dated
    0.38
    oulis
    0.38
     amp
    0.37
    ibal
    0.37
     signal
    0.37
    iejs
    0.36
    Activations Density 0.001%

    No Known Activations