© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 180698
    Prev
    Next
    INDEX
    Explanations

    multilingual content and code

    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_24_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
    ร้อม
    0.40
    檤
    0.40
    प्प
    0.40
     ຮ
    0.40
    forestation
    0.39
    ?')
    0.39
     lle
    0.38
    㐱
    0.38
     ?)
    0.38
     vot
    0.37
    POSITIVE LOGITS
     vague
    0.42
     complicated
    0.39
     個人
    0.38
    MP
    0.37
    実は
    0.36
     बाव
    0.36
     English
    0.34
     MP
    0.34
     моги
    0.34
    jev
    0.34
    Activations Density 0.000%

    No Known Activations