© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 129924
    Prev
    Next
    INDEX
    Explanations

    cache behavior

    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_25_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
    硝
    0.37
     hasten
    0.35
    ктак
    0.34
    コス
    0.34
    Solving
    0.34
    lici
    0.34
    lada
    0.33
    [{\
    0.33
    Electronics
    0.33
    ходе
    0.32
    POSITIVE LOGITS
     unassuming
    0.36
     आधा
    0.35
     willkommen
    0.35
     limité
    0.35
     stå
    0.34
     Winner
    0.34
     Pern
    0.34
     বুলেট
    0.34
     Merr
    0.33
     metà
    0.33
    Activations Density 0.004%

    No Known Activations