© 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
    2. Gemma-3-27B-IT
    3. 46-GEMMASCOPE-2-TRANSCODER-262K
    4. 66237
    Prev
    Next
    INDEX
    Explanations

    fictional titles

    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
    houette
    0.36
    iere
    0.34
    ransition
    0.34
    isbury
    0.34
     فائلوں
    0.33
    ரள
    0.32
    晗
    0.32
    arie
    0.31
    ঁচু
    0.31
     exaggeration
    0.31
    POSITIVE LOGITS
     글로벌
    0.34
     unhappy
    0.32
     CLA
    0.32
     vare
    0.32
     所
    0.32
     lanjut
    0.31
     HALL
    0.31
     VON
    0.30
    телями
    0.30
     ejec
    0.30
    Activations Density 0.003%

    No Known Activations