© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 6930
    Prev
    Next
    INDEX
    Explanations

    be

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_44_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    áře
    0.41
    再生
    0.37
    ressor
    0.37
    ář
    0.36
     Pec
    0.36
     වැඩි
    0.36
     Yankee
    0.35
    agner
    0.35
    沸
    0.35
    abase
    0.35
    POSITIVE LOGITS
     سريع
    0.40
     adventurous
    0.39
    }|^
    0.38
    моль
    0.38
     beauty
    0.37
     proactive
    0.37
     красо
    0.37
    beauty
    0.37
    祟
    0.36
     quicker
    0.36
    Activations Density 0.000%

    No Known Activations