© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 27325
    Prev
    Next
    INDEX
    Explanations

    supermarket and retail locations

    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_10_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
     телефона
    0.63
     pioneering
    0.61
    陘
    0.59
     Syk
    0.59
    ాడు
    0.58
     apache
    0.58
     synergistic
    0.57
     जगह
    0.57
     hostel
    0.57
    ᚨ
    0.57
    POSITIVE LOGITS
    ون
    0.84
    it
    0.82
    on
    0.82
    is
    0.76
    ي
    0.76
    ר
    0.74
    i
    0.72
    ח
    0.70
    ح
    0.69
    and
    0.68
    Activations Density 0.001%

    No Known Activations