© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 17573
    Prev
    Next
    INDEX
    Explanations

    beginning of html

    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_34_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
     trich
    0.45
     shortest
    0.41
    నుక
    0.39
    纜
    0.39
     odyssey
    0.37
     quickest
    0.37
    enterprise
    0.37
    ುದು
    0.37
     Av
    0.36
     simplest
    0.36
    POSITIVE LOGITS
    ITIVE
    0.40
    🏼
    0.36
    🆙
    0.36
    irnov
    0.35
     নির্বাচনে
    0.35
    朵
    0.34
    ныя
    0.34
    ceğim
    0.34
    ✻
    0.34
    ortion
    0.34
    Activations Density 0.000%

    No Known Activations