© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 232181
    Prev
    Next
    INDEX
    Explanations

    during

    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_32_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
    ковь
    0.43
     फोटोशूट
    0.37
    auso
    0.35
    восто
    0.34
    Worst
    0.34
     riguardo
    0.34
    ץ
    0.34
    вого
    0.32
     رکھنے
    0.32
     رابطہ
    0.32
    POSITIVE LOGITS
    adar
    0.42
     química
    0.40
     Química
    0.36
     Mad
    0.36
    ]._
    0.36
    ထိ
    0.35
     tightly
    0.35
     Mak
    0.35
    ].
    0.34
     presença
    0.34
    Activations Density 0.001%

    No Known Activations