© 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. 21847
    Prev
    Next
    INDEX
    Explanations

    d

    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
    ığın
    0.39
    Jogador
    0.37
    ITCH
    0.37
    ᅵ
    0.37
    စ်
    0.37
     ['.
    0.36
    kt
    0.36
    ('.
    0.35
    asso
    0.35
     Assn
    0.35
    POSITIVE LOGITS
    зино
    0.38
     venture
    0.37
    зин
    0.36
     venturing
    0.35
    出的
    0.35
    UNIC
    0.34
     ventured
    0.34
     unbear
    0.34
    encio
    0.34
     createArticle
    0.34
    Activations Density 0.000%

    No Known Activations