© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 204000
    Prev
    Next
    INDEX
    Explanations

    Estonia

    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_46_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
    ryption
    0.39
    ulence
    0.39
    損
    0.38
     all
    0.37
    abilité
    0.37
    forEach
    0.36
     bài
    0.36
    aments
    0.35
     blo
    0.35
    abilit
    0.35
    POSITIVE LOGITS
     expecting
    0.39
    Bend
    0.37
    ង
    0.36
     espaços
    0.36
    בוע
    0.36
     десять
    0.36
    Expect
    0.36
    Ding
    0.35
    ន្ធ
    0.35
     CommandCenter
    0.35
    Activations Density 0.001%

    No Known Activations