© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 50559
    Prev
    Next
    INDEX
    Explanations

    say digits

    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_55_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
    iceras
    0.43
    plers
    0.40
    ()`
    0.39
     `
    0.36
     Kershaw
    0.36
     Header
    0.35
    ()}
    0.35
     среды
    0.35
    ુ
    0.35
     зап
    0.35
    POSITIVE LOGITS
     Bake
    0.39
    AV
    0.36
    lty
    0.36
    Clay
    0.36
     নয়
    0.35
     Mille
    0.35
    Hank
    0.35
    えている
    0.34
    Შ
    0.34
    リティ
    0.33
    Activations Density 0.002%

    No Known Activations