© 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. 12789
    Prev
    Next
    INDEX
    Explanations

    html parsing

    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
    靠
    0.41
    reliance
    0.39
     ब्ले
    0.38
     Signal
    0.37
     நம்பிக்கை
    0.36
    ̣n
    0.36
    coe
    0.36
     SIGNAL
    0.36
     Identity
    0.35
    ︶
    0.35
    POSITIVE LOGITS
    argsort
    0.44
     stern
    0.41
    ApiResponse
    0.38
    usnya
    0.38
     nay
    0.37
    ھوں
    0.37
     disinterested
    0.37
     Stern
    0.36
    ところ
    0.36
     Uran
    0.35
    Activations Density 0.110%

    No Known Activations