© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 32259
    Prev
    Next
    INDEX
    Explanations

    supporting material

    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_7_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
    isting
    0.38
     I
    0.37
    ،
    0.37
    。.
    0.37
    ina
    0.36
    imia
    0.36
    isão
    0.34
     आणि
    0.34
    islava
    0.34
    erten
    0.33
    POSITIVE LOGITS
    મ
    0.39
    تم
    0.39
    지
    0.39
     iPod
    0.38
    ب
    0.38
     bowels
    0.37
    zelfde
    0.37
     umpire
    0.37
    де
    0.37
     microphone
    0.37
    Activations Density 0.023%

    No Known Activations