© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 235039
    Prev
    Next
    INDEX
    Explanations

    audience type

    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_32_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
     nominee
    0.39
     rámci
    0.39
     intermediary
    0.39
     clients
    0.38
     dirigeants
    0.38
     trim
    0.37
     consommateurs
    0.37
    侣
    0.37
     citizens
    0.36
     cittadini
    0.36
    POSITIVE LOGITS
    おく
    0.38
    кими
    0.38
     banheiro
    0.38
    permissionid
    0.37
    чества
    0.36
     setor
    0.36
    WARF
    0.36
    йки
    0.35
    编制
    0.35
    зе
    0.35
    Activations Density 0.005%

    No Known Activations