© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 203165
    Prev
    Next
    INDEX
    Explanations

    Literary, literally, lithe

    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_37_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
     multil
    0.42
    Participants
    0.36
    𝓢
    0.35
    participants
    0.34
    LT
    0.34
    লের
    0.34
     debugShow
    0.34
    ственные
    0.34
    apie
    0.34
     epis
    0.33
    POSITIVE LOGITS
    ္
    0.38
     livros
    0.37
     unavoid
    0.36
     JAC
    0.35
     книга
    0.35
    უთ
    0.35
    둣
    0.34
     পুস্তকের
    0.33
     Dekker
    0.33
     Minden
    0.33
    Activations Density 0.001%

    No Known Activations