© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 210862
    Prev
    Next
    INDEX
    Explanations

    credits rolled

    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
    RUP
    0.45
     спро
    0.44
    RON
    0.42
     Imágenes
    0.42
     காட்டு
    0.41
    HDL
    0.40
    流
    0.40
    akkha
    0.39
    ására
    0.39
    rym
    0.38
    POSITIVE LOGITS
    वीय
    0.49
    anjutan
    0.46
    ס
    0.44
     Wrigley
    0.44
     पहनी
    0.43
     รวมถึง
    0.43
     terminou
    0.43
    จัด
    0.43
     homework
    0.42
    ਸ
    0.42
    Activations Density 0.000%

    No Known Activations