© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 40076
    Prev
    Next
    INDEX
    Explanations

    model

    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_57_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
    Bep
    0.41
    HLIGHT
    0.38
    Fol
    0.37
    漠
    0.36
     Wi
    0.35
    ጨ
    0.35
     vaz
    0.35
    মুনা
    0.35
    គ្
    0.34
     Fol
    0.34
    POSITIVE LOGITS
    ngày
    0.41
     yeri
    0.39
     উচ্চারণ
    0.37
    ーク
    0.37
    Sandy
    0.36
    ষ্কার
    0.36
     خارجه
    0.36
    daniel
    0.35
    kish
    0.34
     즐
    0.34
    Activations Density 0.008%

    No Known Activations