© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 77244
    Prev
    Next
    INDEX
    Explanations

    worksheets and books

    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_31_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
     Zusch
    0.42
    头发
    0.37
     القر
    0.36
    랬
    0.36
     auricular
    0.36
    ayak
    0.34
    chair
    0.33
     protop
    0.33
    তই
    0.33
    懺
    0.33
    POSITIVE LOGITS
     Hartley
    0.38
     Wrigley
    0.36
     phy
    0.36
    蔽
    0.36
    痪
    0.36
    פט
    0.35
     Luc
    0.34
    urón
    0.34
    avr
    0.33
    মিক
    0.33
    Activations Density 0.000%

    No Known Activations