© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 50787
    Prev
    Next
    INDEX
    Explanations

    German "mir" or personal statements

    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
     рыб
    0.49
     ένας
    0.48
     πι
    0.47
     ε
    0.45
     impressed
    0.45
     restructured
    0.44
     üz
    0.44
     στους
    0.44
     denominada
    0.43
     অভিষ
    0.42
    POSITIVE LOGITS
     sei
    0.52
    로
    0.50
     może
    0.50
    닿
    0.50
    아가
    0.49
    よ
    0.49
    ヨ
    0.49
    ב
    0.48
    Availability
    0.48
     encuentra
    0.48
    Activations Density 0.000%

    No Known Activations