© 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. 242899
    Prev
    Next
    INDEX
    Explanations

    and print

    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
    zzle
    0.46
     Zeal
    0.43
    iritual
    0.40
     kalau
    0.38
    chell
    0.38
     Zealand
    0.38
    沤
    0.38
    Rate
    0.37
    urni
    0.37
     Bloss
    0.37
    POSITIVE LOGITS
     Persian
    0.43
    伊朗
    0.43
     إيران
    0.43
     consentement
    0.42
     İran
    0.42
     $=$
    0.41
     Iranian
    0.41
     ईरानी
    0.41
     computations
    0.40
     persian
    0.40
    Activations Density 0.010%

    No Known Activations