© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 34774
    Prev
    Next
    INDEX
    Explanations

    technical terms

    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_50_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
     K
    0.72
     ک
    0.51
     k
    0.50
    K
    0.49
     bem
    0.47
     الك
    0.47
    Bem
    0.46
     க
    0.46
     К
    0.45
    Ｋ
    0.45
    POSITIVE LOGITS
    gur
    0.40
     UICtrl
    0.40
    דות
    0.39
    աղ
    0.39
    條
    0.38
     назад
    0.36
    佐
    0.36
     dri
    0.35
     warranties
    0.35
    Nah
    0.34
    Activations Density 0.026%

    No Known Activations