© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 132530
    Prev
    Next
    INDEX
    Explanations

    shoo

    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_1_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
    า
    1.43
    ري
    1.30
    ോ
    1.27
    是
    1.26
    }
    1.23
    ىن
    1.09
    는
    1.08
    ో
    1.05
     která
    1.04
    氀
    1.04
    POSITIVE LOGITS
    st
    1.34
    지
    1.05
    ties
    1.04
    з
    1.01
     retouch
    0.99
    se
    0.98
     stylized
    0.98
    ali
    0.96
    ci
    0.95
    h
    0.93
    Activations Density 0.001%

    No Known Activations