© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 145476
    Prev
    Next
    INDEX
    Explanations

    image formation

    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_18_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
    Depuis
    0.37
    Explanation
    0.34
    এখন
    0.34
     savent
    0.34
    船
    0.34
    Since
    0.33
    Discount
    0.33
    ఎ
    0.33
    Um
    0.32
    Se
    0.32
    POSITIVE LOGITS
     UICtrl
    0.37
     unwelcome
    0.37
    iertas
    0.37
     counterv
    0.36
    ıt
    0.36
     বিদ্যমান
    0.35
     الحالي
    0.35
     hảo
    0.34
     einzelnen
    0.33
    inois
    0.33
    Activations Density 0.001%

    No Known Activations