© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 231654
    Prev
    Next
    INDEX
    Explanations

    closing parentheses for plots

    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
    ва
    1.09
    ி
    1.07
    ри
    1.03
    ).\
    0.96
    á
    0.96
    ції
    0.91
    ın
    0.89
    ‌های
    0.89
    osť
    0.89
    ন
    0.89
    POSITIVE LOGITS
    ER
    1.05
     at
    1.03
    ：
    0.94
    at
    0.93
    ר
    0.88
    ด
    0.87
    ，
    0.86
     polynomial
    0.84
     （
    0.83
     diagram
    0.83
    Activations Density 0.009%

    No Known Activations