© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 174121
    Prev
    Next
    INDEX
    Explanations

    ISBN identifier

    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_20_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
    iativa
    0.40
     فَ
    0.40
    싫
    0.39
    試
    0.39
     nymphs
    0.38
     ګرځ
    0.36
     கி
    0.36
     싫
    0.36
    ্স্ট
    0.35
     flops
    0.35
    POSITIVE LOGITS
    calculations
    0.41
     Calculation
    0.41
     न्यूमेरिकल
    0.38
     Numerical
    0.36
     Transitional
    0.36
     Calculations
    0.35
    Calcul
    0.35
     ngay
    0.35
     incremento
    0.35
     મહત્વ
    0.35
    Activations Density 0.000%

    No Known Activations