© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 106416
    Prev
    Next
    INDEX
    Explanations

    import random

    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_1_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
    ة
    1.43
    </strong>
    1.21
    </u>
    1.13
     be
    1.09
    </span>
    1.04
    "
    1.03
    </h2>
    1.02
    </em>
    1.01
     sua
    0.99
    ።
    0.98
    POSITIVE LOGITS
    ,
    1.45
    IL
    1.14
    EL
    0.95
    ES
    0.92
    0.92
    ss
    0.91
     IL
    0.91
    다
    0.91
     AY
    0.87
     ES
    0.86
    Activations Density 0.001%

    No Known Activations