© 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. 19-GEMMASCOPE-2-TRANSCODER-262K
    7. 209331
    Prev
    Next
    INDEX
    Explanations

    `id`, `name`, `true`

    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_19_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
    ánicas
    0.48
     существуют
    0.47
     <=
    0.44
    alnız
    0.44
     только
    0.44
    青
    0.43
    Options
    0.43
    <=
    0.43
     údaje
    0.42
     тем
    0.42
    POSITIVE LOGITS
    ਰ
    0.53
    ਨ
    0.47
    ўнай
    0.46
    czek
    0.45
    কদের
    0.45
    ɴ
    0.45
     Marlene
    0.44
     maternity
    0.44
    να
    0.43
     toddler
    0.43
    Activations Density 0.001%

    No Known Activations