© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 236456
    Prev
    Next
    INDEX
    Explanations

    computer code

    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_46_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
     систему
    0.39
    ඳ
    0.38
     behandelt
    0.38
     circon
    0.37
     arred
    0.37
    zones
    0.37
     Butch
    0.36
     बें
    0.36
     மண்ட
    0.36
     Mitar
    0.36
    POSITIVE LOGITS
     जीवा
    0.42
    makes
    0.40
    making
    0.36
     \|_{
    0.36
     reqParams
    0.36
    มาณ
    0.35
     Symmetric
    0.35
    ковать
    0.35
    Greetings
    0.34
    렛
    0.34
    Activations Density 0.001%

    No Known Activations