© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 68571
    Prev
    Next
    INDEX
    Explanations

    vowels

    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_46_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
    Az
    0.51
    atiche
    0.47
    
    0.42
     az
    0.42
    روط
    0.40
    ⊷
    0.40
    Plan
    0.40
    तरे
    0.40
     விட்ட
    0.39
    elic
    0.39
    POSITIVE LOGITS
    ynit
    0.44
    ườ
    0.43
    窅
    0.39
    वाईसी
    0.38
    ၽ
    0.38
    yout
    0.38
    ycl
    0.38
     Valk
    0.38
    hler
    0.36
     yawn
    0.36
    Activations Density 0.002%

    No Known Activations