© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 46967
    Prev
    Next
    INDEX
    Explanations

    setProperty/getProperty

    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_13_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
    apes
    0.54
    Sach
    0.53
    KO
    0.52
    ிறேன்
    0.52
    ambiente
    0.51
    apan
    0.51
    🆁
    0.50
    U
    0.50
     environments
    0.50
    oto
    0.49
    POSITIVE LOGITS
    ৯
    0.55
    左
    0.54
     chans
    0.52
    )，
    0.51
    seleccion
    0.51
    freien
    0.50
    цер
    0.49
    ]$;
    0.49
    блю
    0.49
    ജ്
    0.48
    Activations Density 0.000%

    No Known Activations