© 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. 62753
    Prev
    Next
    INDEX
    Explanations

    first

    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
    時間
    0.44
    time
    0.43
     &
    0.41
    ceğ
    0.39
    ҳа
    0.39
    രുവ
    0.39
    hika
    0.39
    asonic
    0.39
    axanthin
    0.38
    ැන
    0.38
    POSITIVE LOGITS
     differences
    0.64
     moment
    0.55
    /$
    0.53
     difference
    0.51
     diferencias
    0.51
     differ
    0.48
     différences
    0.48
     most
    0.48
     Differences
    0.47
     verschill
    0.46
    Activations Density 0.004%

    No Known Activations