© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 213010
    Prev
    Next
    INDEX
    Explanations

    mouth concepts

    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_5_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
    al
    1.26
    r
    1.23
    s
    1.05
    t
    1.01
    ู
    1.00
    ある
    0.98
    c
    0.93
    ας
    0.92
     theological
    0.91
    un
    0.91
    POSITIVE LOGITS
    리
    1.44
    사
    1.40
    لم
    1.32
    มัน
    1.32
    ן
    1.28
    ל
    1.27
    ي
    1.27
    في
    1.23
    它可以
    1.21
     имена
    1.21
    Activations Density 0.000%

    No Known Activations