© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 89137
    Prev
    Next
    INDEX
    Explanations

    radiology

    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
    ם
    0.46
    os
    0.43
    ных
    0.43
    ется
    0.43
    ments
    0.41
    MENTS
    0.40
     KER
    0.38
    рово
    0.37
    咪
    0.37
    вых
    0.37
    POSITIVE LOGITS
    at
    0.52
    )\
    0.43
    oden
    0.41
    Telefon
    0.40
    ator
    0.40
    atel
    0.40
    Logan
    0.40
    ati
    0.39
    aughey
    0.39
    /√
    0.38
    Activations Density 0.000%

    No Known Activations