© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 122915
    Prev
    Next
    INDEX
    Explanations

    flag parsing and definition

    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_37_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
     ஹா
    0.39
     signaling
    0.39
    열
    0.36
    邕
    0.36
     بتت
    0.35
    热
    0.35
     pointing
    0.34
    晕
    0.34
     trovato
    0.34
     উঠলো
    0.34
    POSITIVE LOGITS
     penggunaan
    0.39
     incision
    0.39
     Sake
    0.38
     Saut
    0.37
     Usage
    0.37
     dokument
    0.36
     Dieter
    0.36
    प्पा
    0.36
     父
    0.36
     ImageIcon
    0.35
    Activations Density 0.000%

    No Known Activations