© 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. 7580
    Prev
    Next
    INDEX
    Explanations

    differential geometry

    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
    devDependencies
    0.39
    ਘ
    0.38
     Duane
    0.36
    단의
    0.36
     Тихо
    0.35
    ⊤
    0.35
     высокой
    0.35
    दित
    0.35
    욕
    0.35
    emor
    0.35
    POSITIVE LOGITS
     Kähler
    0.44
     symplectic
    0.43
     podkre
    0.41
     Sy
    0.40
    Kah
    0.40
    Sy
    0.40
     Contact
    0.39
     Symfony
    0.38
     sy
    0.38
     Kah
    0.37
    Activations Density 0.011%

    No Known Activations