© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 97698
    Prev
    Next
    INDEX
    Explanations

    up spills

    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_14_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
    maso
    0.59
    ULONG
    0.59
    lisi
    0.55
    ennan
    0.55
    ⁤
    0.55
    NESS
    0.54
    hane
    0.53
    hound
    0.53
    reicher
    0.53
    渊
    0.53
    POSITIVE LOGITS
     quatre
    0.64
    四年
    0.61
     dwóch
    0.57
     vendedor
    0.57
    키
    0.57
     dört
    0.56
    ཇ
    0.53
     trois
    0.52
     niveau
    0.52
    5
    0.52
    Activations Density 0.001%

    No Known Activations