© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 135556
    Prev
    Next
    INDEX
    Explanations

    ставить (to put/place)

    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_6_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
    ’
    1.36
    ной
    1.05
     fuerza
    1.00
     competencias
    0.95
    薈
    0.94
     mercanc
    0.92
    िंग्स
    0.91
     tarifas
    0.91
    ная
    0.89
    中标
    0.89
    POSITIVE LOGITS
    t
    1.30
    ad
    1.29
    c
    1.29
    ate
    1.23
    AD
    1.13
    다
    1.05
     embroiled
    1.03
    на
    0.98
    6
    0.96
    KER
    0.95
    Activations Density 0.001%

    No Known Activations