© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 38010
    Prev
    Next
    INDEX
    Explanations

    breaking down into categories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_11_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
     l
    0.79
     a
    0.76
    ↵
    0.75
     an
    0.75
     c
    0.73
     la
    0.73
     d
    0.71
    ]
    0.71
     point
    0.69
     le
    0.68
    POSITIVE LOGITS
    بر
    0.70
    hitva
    0.70
    baiki
    0.69
    拶
    0.69
    Autres
    0.66
    До
    0.65
    πει
    0.64
    insensitive
    0.64
    چه
    0.64
    ए
    0.64
    Activations Density 0.034%

    No Known Activations