© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 252832
    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_56_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
    цтва
    0.41
    \&
    0.39
    ecirc
    0.38
    ਾਰ
    0.37
    👛
    0.37
     Și
    0.36
    kowitz
    0.36
    нина
    0.36
    ကိုယ်
    0.36
    rí
    0.36
    POSITIVE LOGITS
     utilis
    0.41
    styl
    0.40
     stylist
    0.40
    羊
    0.38
     CRED
    0.38
     v
    0.38
     styl
    0.38
    lv
    0.38
     LV
    0.38
     vou
    0.37
    Activations Density 0.002%

    No Known Activations