© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 82413
    Prev
    Next
    INDEX
    Explanations

    In

    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_53_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
    𝑯
    0.38
     फुले
    0.37
    เรียน
    0.35
    ন্তী
    0.35
    טל
    0.35
    érist
    0.34
     اتا
    0.33
     रुग्ण
    0.33
    <\
    0.32
     ㅇ
    0.32
    POSITIVE LOGITS
     formation
    2.11
    formation
    2.08
    forming
    2.00
     formación
    1.97
    形成
    1.95
    Formation
    1.95
    form
    1.95
    Form
    1.94
     Formation
    1.94
     formação
    1.93
    Activations Density 0.004%

    No Known Activations