© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 27062
    Prev
    Next
    INDEX
    Explanations

    code blocks with method/function definitions

    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
     chocolate
    0.43
    Chocolate
    0.43
     Chocolate
    0.42
     шокола
    0.40
    巧克力
    0.40
     realized
    0.39
    zá
    0.39
    渴
    0.39
     चॉकलेट
    0.38
     expectativa
    0.38
    POSITIVE LOGITS
     succession
    0.38
     Annotation
    0.38
    sdx
    0.36
    誦
    0.36
    ServerError
    0.35
    汉
    0.35
     சேர்ந்த
    0.35
     presumption
    0.35
     sådan
    0.34
    ння
    0.34
    Activations Density 0.000%

    No Known Activations