© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 45501
    Prev
    Next
    INDEX
    Explanations

    cuban missile, malloc, cuban peso

    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_3_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
    á
    0.93
    j
    0.79
    g
    0.76
    k
    0.74
     coupe
    0.67
     Coupe
    0.65
    де
    0.64
    il
    0.62
    coupon
    0.62
    ich
    0.61
    POSITIVE LOGITS
    ش
    0.96
    ש
    0.93
    स
    0.93
    י
    0.91
    ב
    0.91
    ح
    0.89
    ل
    0.88
    د
    0.85
    ي
    0.82
    ל
    0.80
    Activations Density 0.006%

    No Known Activations