© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 17561
    Prev
    Next
    INDEX
    Explanations

    first step

    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_40_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
     DEALINGS
    0.41
     وخت
    0.34
     bracket
    0.34
    ﺡ
    0.34
    üe
    0.34
    нее
    0.33
    㜌
    0.33
    جز
    0.33
    ocard
    0.33
    éraire
    0.33
    POSITIVE LOGITS
     first
    1.07
    第一
    1.07
     ersten
    1.02
     erste
    1.01
     første
    1.01
     första
    1.01
     eerste
    0.97
     첫
    0.97
     पहला
    0.96
     первый
    0.96
    Activations Density 0.237%

    No Known Activations