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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 197918
    Prev
    Next
    INDEX
    Explanations

    URLs and file paths

    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_27_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
    荣
    0.40
    妽
    0.39
    Honeycomb
    0.38
     pretzel
    0.38
     conductance
    0.38
    Conduct
    0.36
    🏞
    0.36
     þat
    0.36
     honeycomb
    0.36
     нега
    0.35
    POSITIVE LOGITS
    guess
    0.40
     separados
    0.39
     tiros
    0.38
     عارفين
    0.38
     Obr
    0.38
     maggiori
    0.38
    辏
    0.38
    separate
    0.37
    str
    0.36
     Tokio
    0.35
    Activations Density 0.001%

    No Known Activations