© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 203503
    Prev
    Next
    INDEX
    Explanations

    caused by

    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_6_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
    X
    1.01
    th
    1.00
    RA
    0.94
    ig
    0.91
    지
    0.90
    as
    0.89
    IL
    0.87
    RI
    0.87
    ET
    0.86
    Y
    0.85
    POSITIVE LOGITS
    mimpi
    1.00
    ू
    0.90
    ری
    0.88
    रा
    0.84
    ور
    0.83
    )
    0.83
    ه
    0.82
    ιου
    0.81
    ः
    0.81
    на
    0.81
    Activations Density 0.002%

    No Known Activations