© 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. 205537
    Prev
    Next
    INDEX
    Explanations

    MTBF

    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
    ↵↵
    1.34
    س
    1.09
    s
    0.98
    า
    0.98
    1
    0.97
    ี
    0.96
     s
    0.92
    ä
    0.85
    "
    0.83
    f
    0.82
    POSITIVE LOGITS
     فيلم
    1.08
     டிகிரி
    1.05
     દરમિયાન
    1.02
    ků
    1.02
     فونبټ
    1.01
    știg
    1.01
     Timurtaş
    1.00
     Cnemidophorus
    1.00
    ឡិចត្រូ
    1.00
     CORPER
    0.99
    Activations Density 0.000%

    No Known Activations