© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 163812
    Prev
    Next
    INDEX
    Explanations

    release notes or mechanics

    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_13_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
     Brass
    0.49
    ǒu
    0.49
    פּ
    0.47
    یشه
    0.47
     ሕ
    0.47
     micrófono
    0.47
    य्
    0.47
     тай
    0.47
     prerog
    0.47
     subtraction
    0.47
    POSITIVE LOGITS
    _
    0.53
     দক্ষ
    0.52
    层
    0.51
     darunter
    0.47
    埋
    0.47
     với
    0.45
    Generated
    0.45
     फैला
    0.45
    着
    0.45
    多
    0.44
    Activations Density 0.000%

    No Known Activations