© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 43998
    Prev
    Next
    INDEX
    Explanations

    documentation links

    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_13_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
    ن
    0.17
    和
    0.15
    (
    0.15
    Entity
    0.14
    ，
    0.14
    是
    0.14
    以
    0.14
    리
    0.14
    以便
    0.14
    དང་
    0.13
    POSITIVE LOGITS
     sentirse
    0.17
     bootcamp
    0.15
     പെ
    0.14
     بیر
    0.13
    ueta
    0.13
     уче
    0.13
     nightclub
    0.13
    quilla
    0.13
     peruse
    0.13
     acredit
    0.13
    Activations Density 0.004%

    No Known Activations