© 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. 12226
    Prev
    Next
    INDEX
    Explanations

    let me

    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
     write
    0.45
     escribe
    0.44
     wrote
    0.43
     Writes
    0.43
     writes
    0.43
     пишу
    0.41
     dere
    0.40
     写
    0.40
     HB
    0.40
     scrive
    0.40
    POSITIVE LOGITS
     REGI
    0.38
     قواعد
    0.36
    远的
    0.35
     thầy
    0.35
    اقه
    0.34
    öre
    0.34
     फर
    0.34
     দুর্ঘট
    0.34
     තර
    0.34
     hồ
    0.33
    Activations Density 0.002%

    No Known Activations