© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 2313
    Prev
    Next
    INDEX
    Explanations

    kubernetes api version

    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_40_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
     persisting
    0.39
    Persistent
    0.38
    persistent
    0.37
    Pers
    0.35
    甾
    0.35
    SQ
    0.35
     حجم
    0.35
     Persistent
    0.35
     PERS
    0.35
    Acetyl
    0.35
    POSITIVE LOGITS
     V
    0.41
    Den
    0.38
    ialog
    0.38
     URI
    0.38
    δή
    0.37
    Ze
    0.37
    ury
    0.36
    Der
    0.36
     Desktop
    0.35
     Vish
    0.35
    Activations Density 0.001%

    No Known Activations