© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 207398
    Prev
    Next
    INDEX
    Explanations

    total

    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_25_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
    пъл
    0.38
    ERICK
    0.37
     ćel
    0.37
     נישט
    0.36
    寸
    0.36
     ansch
    0.36
    yrıca
    0.35
    removeFrom
    0.35
     şart
    0.35
    łącznie
    0.35
    POSITIVE LOGITS
     quadru
    0.38
     విజ
    0.37
    高雄
    0.37
    矚
    0.36
     proof
    0.35
     enormous
    0.35
     Manuel
    0.35
     উপ
    0.35
     impasse
    0.34
     inequality
    0.34
    Activations Density 0.003%

    No Known Activations