© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 10309
    Prev
    Next
    INDEX
    Explanations

    auxiliary verbs and 's suffix

    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_13_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
     nicest
    0.27
    _{\
    0.25
    ^{\
    0.25
    ين
    0.24
    主
    0.23
     toughest
    0.23
    #'
    0.23
    ierrez
    0.23
    EV
    0.22
    量的
    0.22
    POSITIVE LOGITS
    
    0.29
    锭
    0.27
    rás
    0.26
     నమో
    0.26
     mills
    0.25
    ོན་
    0.25
    ‸
    0.25
    ാരണ
    0.25
    sony
    0.24
     Genoa
    0.24
    Activations Density 0.441%

    No Known Activations