© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 5951
    Prev
    Next
    INDEX
    Explanations

    **

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_44_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
    iellement
    0.41
    okol
    0.37
    উল
    0.37
    宣告
    0.36
    dlg
    0.36
     Zachary
    0.35
    дан
    0.35
    谴
    0.34
    reement
    0.34
     mutant
    0.34
    POSITIVE LOGITS
     fyz
    0.45
     фізи
    0.44
    uble
    0.41
     Fiz
    0.41
     仕様
    0.40
     ಶತ
    0.39
     雨
    0.38
     Fiziki
    0.37
     Derby
    0.37
     demod
    0.36
    Activations Density 0.013%

    No Known Activations