© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 237524
    Prev
    Next
    INDEX
    Explanations

    apps like

    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_32_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
     adaptarse
    0.40
     web
    0.39
    טו
    0.38
     웹
    0.37
    web
    0.36
     جی
    0.36
     اهم
    0.36
     prid
    0.36
    烘
    0.36
     निर्वा
    0.35
    POSITIVE LOGITS
     požad
    0.39
     hand
    0.38
     intentionally
    0.38
     bands
    0.37
     berbahaya
    0.35
    際は
    0.35
     مشارکت
    0.35
     bequest
    0.35
    日は
    0.35
    orpion
    0.35
    Activations Density 0.003%

    No Known Activations