© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 159399
    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
     ﺍ
    1.05
     indiquer
    0.96
     midfielders
    0.96
     öğrenciler
    0.95
    К
    0.94
     plasmids
    0.92
    നട
    0.91
    INGS
    0.90
     categor
    0.89
    URS
    0.89
    POSITIVE LOGITS
    س
    1.45
    ні
    1.17
    ق
    1.17
    ang
    1.16
    ன்
    1.15
    是
    1.13
    al
    1.10
    ing
    1.10
    ä
    1.10
    ong
    1.09
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.