© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 215962
    Prev
    Next
    INDEX
    Explanations

    Choroideremia, doggystyle, Cristóbal Colón

    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_5_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     powied
    1.28
    ين
    1.23
     밝혔
    1.17
    ал
    1.06
     рассказа
    1.03
    ال
    1.02
    ه
    1.02
    ان
    1.02
    ض
    1.01
    الأ
    1.00
    POSITIVE LOGITS
    :
    1.09
    al
    1.05
     beauties
    1.03
    d
    1.00
    )
    0.98
    ian
    0.97
    TA
    0.96
     drugih
    0.96
     baseless
    0.92
    𝓭
    0.92
    Activations Density 0.000%

    No Known Activations