© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 89761
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_60_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
     The
    0.50
     and
    0.45
    0.42
     и
    0.42
    6
    0.39
     bulld
    0.38
     fand
    0.38
     andro
    0.38
     Decoder
    0.38
     pom
    0.37
    POSITIVE LOGITS
    ات
    0.47
    فتح
    0.47
    عر
    0.47
    ווע
    0.46
    વ
    0.46
    يش
    0.45
    إ
    0.45
    having
    0.44
    بي
    0.44
    تب
    0.44
    Activations Density 0.000%

    No Known Activations