© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 161900
    Prev
    Next
    INDEX
    Explanations

    oled, driving, ripped

    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_2_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
    ل
    1.61
    ر
    1.45
    자
    1.35
    ט
    1.34
    ال
    1.32
    ت
    1.31
    1.27
     It
    1.25
    ان
    1.20
    ת
    1.19
    POSITIVE LOGITS
     firmado
    0.94
     be
    0.93
    ched
    0.86
    en
    0.85
     zatim
    0.84
     have
    0.83
     було
    0.82
    enti
    0.80
     তথা
    0.80
     שה
    0.80
    Activations Density 0.000%

    No Known Activations