© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 107402
    Prev
    Next
    INDEX
    Explanations

    awk scripts

    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_2_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
    :
    1.06
    ak
    1.05
    8
    0.89
    UM
    0.82
    TS
    0.82
    ant
    0.81
     مثال
    0.81
    :>
    0.79
    OS
    0.79
     atteindre
    0.77
    POSITIVE LOGITS
    s
    1.38
    0.97
    ی
    0.93
    ве
    0.93
    I
    0.92
    v
    0.88
    to
    0.88
    ки
    0.87
     It
    0.86
    ى
    0.86
    Activations Density 0.001%

    No Known Activations