© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 165176
    Prev
    Next
    INDEX
    Explanations

    Penhaligon

    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_13_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
    ючи
    0.59
    ]_{
    0.55
    ਹੀਂ
    0.50
    worker
    0.49
    ורה
    0.49
    卿
    0.48
    iences
    0.48
     연료
    0.48
    recovered
    0.47
     ವಿ
    0.46
    POSITIVE LOGITS
     September
    0.56
     minden
    0.51
     August
    0.48
    le
    0.48
     Haziran
    0.48
    )”.
    0.47
     leopard
    0.47
     October
    0.47
    }).
    0.47
    レ
    0.47
    Activations Density 0.003%

    No Known Activations