© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 43768
    Prev
    Next
    INDEX
    Explanations

    academic rigor

    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_3_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
    '
    0.85
    EN
    0.78
    ’
    0.71
    1
    0.70
    OD
    0.69
     on
    0.68
    ink
    0.68
    ES
    0.68
    OW
    0.67
     medis
    0.66
    POSITIVE LOGITS
    même
    0.67
    ח
    0.65
    ان
    0.62
    রা
    0.62
    рены
    0.61
    на
    0.58
    ار
    0.58
    можно
    0.58
     واي
    0.58
    también
    0.58
    Activations Density 0.003%

    No Known Activations