© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 51498
    Prev
    Next
    INDEX
    Explanations

    news anchor introductions

    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_30_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
     ilustración
    0.39
    Observ
    0.38
     многи
    0.36
     છ
    0.36
     улы
    0.36
     uninterrupted
    0.35
     Organización
    0.35
     அமைந்துள்ளது
    0.35
    otoxicity
    0.35
    突き
    0.35
    POSITIVE LOGITS
     ενός
    0.44
     sebuah
    0.43
     an
    0.42
     isang
    0.41
     een
    0.39
     a
    0.39
     einem
    0.39
     triggers
    0.38
     harrow
    0.38
     einer
    0.38
    Activations Density 0.005%

    No Known Activations