© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 36596
    Prev
    Next
    INDEX
    Explanations

    -blatt, -esp, er, -etti, -us, -aria, -bl, -by, -eng, -ary

    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
    un
    1.00
    ب
    0.84
    uk
    0.83
    és
    0.74
    ul
    0.71
    ول
    0.71
    ن
    0.70
    مع
    0.70
    r
    0.70
    ي
    0.69
    POSITIVE LOGITS
    0.88
     femmes
    0.70
    ᱗
    0.64
     ای
    0.63
     publicité
    0.62
     interviewing
    0.61
     가
    0.60
     çox
    0.60
    ૨
    0.59
     badan
    0.59
    Activations Density 0.001%

    No Known Activations