© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 41997
    Prev
    Next
    INDEX
    Explanations

    percentage of

    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_22_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
     looted
    0.23
     cunning
    0.21
    Civil
    0.21
    Пла
    0.20
    ধ্ব
    0.20
    Khal
    0.20
     conspicuous
    0.20
    民
    0.20
    хов
    0.20
    РИ
    0.20
    POSITIVE LOGITS
    concept
    0.25
    concepto
    0.22
    afil
    0.21
    .)
    0.21
    af
    0.20
    ven
    0.20
    ur
    0.20
     مفهوم
    0.20
     هفت
    0.20
    aug
    0.20
    Activations Density 0.007%

    No Known Activations