© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 167102
    Prev
    Next
    INDEX
    Explanations

    key

    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
    Ele
    0.33
    Plain
    0.32
    WW
    0.31
    Arnold
    0.30
    
    0.30
    BJ
    0.30
    ルイ
    0.30
    Si
    0.29
    spe
    0.29
    Globalization
    0.29
    POSITIVE LOGITS
     ключ
    0.40
     kunci
    0.35
     key
    0.34
    чан
    0.34
     llave
    0.34
     без
    0.33
     senza
    0.33
     chave
    0.33
    ikey
    0.32
     на
    0.32
    Activations Density 0.001%

    No Known Activations