© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 19310
    Prev
    Next
    INDEX
    Explanations

    I'll cover:

    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_15_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
     کننده
    0.49
    ೂರ್ವ
    0.45
    зыка
    0.41
     علاوه
    0.40
    Qnt
    0.39
    ोरा
    0.39
    ो
    0.38
     Dương
    0.38
     داخ
    0.38
     අන
    0.38
    POSITIVE LOGITS
    at
    0.48
     satire
    0.41
    the
    0.40
    ip
    0.40
    topics
    0.38
    æ
    0.38
     topics
    0.38
    daki
    0.37
    新聞
    0.37
    ab
    0.37
    Activations Density 0.110%

    No Known Activations