© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 89980
    Prev
    Next
    INDEX
    Explanations

    Margaret

    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_60_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
    3
    0.68
    ↵↵
    0.66
    playing
    0.61
    The
    0.57
    cropping
    0.56
    hitting
    0.54
    key
    0.53
    -
    0.53
    play
    0.53
    domains
    0.52
    POSITIVE LOGITS
     li
    0.65
     Li
    0.63
     l
    0.58
     Unite
    0.58
     Eee
    0.57
     KI
    0.57
     Vanilla
    0.57
     Ui
    0.56
     Vasa
    0.56
     Un
    0.54
    Activations Density 0.000%

    No Known Activations