© 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. 9182
    Prev
    Next
    INDEX
    Explanations

    professional publication citations

    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
    檳
    0.38
     Tudor
    0.38
     প্রোগ্রাম
    0.38
     Rochester
    0.36
     Somehow
    0.36
     Pancakes
    0.35
     hypersur
    0.35
     Şimdi
    0.35
     plage
    0.35
     '.</
    0.35
    POSITIVE LOGITS
     Notices
    0.42
    bock
    0.40
    ക്കാര
    0.39
    beet
    0.37
     ਕਰਨ
    0.37
    Zee
    0.36
    沌
    0.35
     biol
    0.35
     pure
    0.34
     Phi
    0.34
    Activations Density 0.039%

    No Known Activations