© 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. 13565
    Prev
    Next
    INDEX
    Explanations

    `https://` URLs in HTML tags

    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
     Diameter
    0.25
    тим
    0.24
     निप
    0.23
     ভঙ্গ
    0.22
    형
    0.22
    ಿತ
    0.22
    форма
    0.22
     nChar
    0.21
     광
    0.21
    藍
    0.21
    POSITIVE LOGITS
     writes
    0.26
     adds
    0.25
     monument
    0.24
    PUBLIC
    0.24
    dom
    0.24
     sends
    0.23
    luc
    0.23
     propone
    0.23
     appeals
    0.22
     argues
    0.22
    Activations Density 0.001%

    No Known Activations