© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 37559
    Prev
    Next
    INDEX
    Explanations

    multilingual text

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_57_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
    რც
    0.41
     sowas
    0.38
    そう
    0.36
     тща
    0.36
     viscos
    0.36
     چکی
    0.35
    悛
    0.35
    rede
    0.35
     gewinnen
    0.35
    рова
    0.34
    POSITIVE LOGITS
     ведь
    0.46
    Compass
    0.36
    Coral
    0.35
     layering
    0.35
    ế
    0.34
    ≋
    0.34
     Compass
    0.33
    ",'
    0.33
     CM
    0.33
    ड़ब
    0.32
    Activations Density 0.002%

    No Known Activations