© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 61955
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_2_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
                
    1.42
    ক
    1.39
    il
    1.29
    y
    1.20
    er
    1.16
    k
    1.14
    यों
    1.11
    z
    1.10
    ur
    1.08
    ק
    1.07
    POSITIVE LOGITS
    are
    1.05
     as
    1.02
    9
    0.92
    رسٹ
    0.87
    வ்வேறு
    0.84
    0
    0.84
    洙
    0.82
     Bás
    0.78
    薇
    0.77
    臾
    0.76
    Activations Density 0.000%

    No Known Activations