© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 127031
    Prev
    Next
    INDEX
    Explanations

    document.getElementsByTagName or getContext

    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_37_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
    okban
    0.38
    の種類
    0.36
    刦
    0.36
     tipos
    0.36
     retorno
    0.36
    㞖
    0.36
    ন্ত
    0.35
    דור
    0.35
    馗
    0.35
    堈
    0.35
    POSITIVE LOGITS
     स्ट्रा
    0.45
     gifting
    0.39
     cesium
    0.36
    遥
    0.36
    अमेरिकी
    0.36
     lending
    0.35
     Hona
    0.35
    риа
    0.35
    ześnie
    0.34
    ታዊ
    0.34
    Activations Density 0.001%

    No Known Activations