© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 195707
    Prev
    Next
    INDEX
    Explanations

    child

    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_46_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
     Kaufman
    0.41
     guardia
    0.40
     Lafayette
    0.40
     Lune
    0.40
     Darby
    0.38
     Friedman
    0.37
     떨어
    0.36
    뱃
    0.36
     checkout
    0.35
     garde
    0.35
    POSITIVE LOGITS
    reso
    0.42
    Server
    0.40
    mit
    0.39
    YG
    0.38
     YG
    0.38
    })=
    0.38
    sta
    0.38
    ږ
    0.37
    server
    0.37
    Mit
    0.37
    Activations Density 0.002%

    No Known Activations