© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 146835
    Prev
    Next
    INDEX
    Explanations

    technical entities

    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_59_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
     an
    0.57
    house
    0.55
     house
    0.50
    บ้าน
    0.45
    ハウス
    0.44
    House
    0.40
    HOUSE
    0.39
    집
    0.39
    at
    0.38
     place
    0.38
    POSITIVE LOGITS
     rest
    0.58
     Montevideo
    0.44
     Rest
    0.44
    hiddenMap
    0.43
     banda
    0.42
     Kw
    0.41
     Panam
    0.40
    DrvGPIO
    0.38
     ಪ್ಯಾ
    0.38
     pang
    0.38
    Activations Density 0.000%

    No Known Activations