© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-TRANSCODER-262K
    4. 51412
    Prev
    Next
    INDEX
    Explanations

    край, крае, к

    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_31_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
    Herb
    0.40
    ➳
    0.39
    Jersey
    0.37
     Rahim
    0.36
    gies
    0.36
    wirkung
    0.35
    Set
    0.35
     நூ
    0.35
    leaving
    0.35
    鹵
    0.35
    POSITIVE LOGITS
     Bl
    0.42
     fecha
    0.39
     PAC
    0.38
     dates
    0.38
     theme
    0.38
     shortness
    0.38
     maf
    0.37
     marked
    0.37
     Marked
    0.37
     competency
    0.36
    Activations Density 0.003%

    No Known Activations