© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 78724
    Prev
    Next
    INDEX
    Explanations

    places like theaters

    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_0_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
    s
    2.45
    ING
    2.11
    ك
    1.79
    ים
    1.63
    ן
    1.61
    ا
    1.60
    ка
    1.59
    ה
    1.59
    ی
    1.48
    ED
    1.39
    POSITIVE LOGITS
    et
    1.17
     сроки
    1.12
    idina
    1.11
    ட்சத்திர
    1.06
     जहाज
    1.03
     père
    1.02
     rumble
    1.02
     década
    1.02
     EEOC
    1.00
    ascimento
    0.99
    Activations Density 0.000%

    No Known Activations