© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 21560
    Prev
    Next
    INDEX
    Explanations

    text generation

    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_56_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
    ës
    0.38
    sor
    0.36
     ничек
    0.36
     MAIN
    0.36
     À
    0.35
     erfüll
    0.35
    MIR
    0.35
     à
    0.35
    땔
    0.35
    ittances
    0.34
    POSITIVE LOGITS
    Background
    0.44
    द्रा
    0.38
     particuliers
    0.38
    ಚ
    0.37
     `.
    0.35
    lst
    0.35
     Background
    0.34
    Timing
    0.34
    Networking
    0.34
    ,-\
    0.34
    Activations Density 0.030%

    No Known Activations