© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 7629
    Prev
    Next
    INDEX
    Explanations

    questionnaires and surveys

    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
     kayb
    0.41
     "{
    0.41
     Rubi
    0.41
    bamos
    0.40
    താണ്
    0.39
    拍
    0.39
    账户
    0.38
     przek
    0.38
    ⇆
    0.37
     bato
    0.37
    POSITIVE LOGITS
     inventories
    0.42
     inventory
    0.41
     Hintergrund
    0.41
     invent
    0.41
     Tween
    0.40
     reel
    0.39
     Invent
    0.37
     tund
    0.37
     reaper
    0.36
    拣
    0.36
    Activations Density 0.034%

    No Known Activations