© 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. 14234
    Prev
    Next
    INDEX
    Explanations

    rain barrel collects

    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
     تھی۔
    0.58
     IntPtr
    0.54
    тена
    0.54
     ();
    0.52
    一半
    0.52
    戽
    0.51
     (’
    0.50
    。“
    0.49
    🐥
    0.49
     Perché
    0.49
    POSITIVE LOGITS
     as
    0.60
    ไม่
    0.59
    c
    0.57
    き
    0.55
     dos
    0.55
    कों
    0.55
    as
    0.53
     frequented
    0.53
     confidently
    0.52
     inexplic
    0.51
    Activations Density 0.000%

    No Known Activations