© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 157669
    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_50_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
     Loth
    0.43
     RAB
    0.42
     IBC
    0.39
    abba
    0.38
     rai
    0.37
     UNIT
    0.36
     FEST
    0.36
    ﭔ
    0.36
    UNIT
    0.35
    ager
    0.35
    POSITIVE LOGITS
     Kxc
    0.38
     Chico
    0.37
    คม
    0.37
    тером
    0.35
     sharps
    0.34
     تتع
    0.34
    લ્સ
    0.34
    ша
    0.33
     Algebra
    0.33
    ंमुळे
    0.33
    Activations Density 0.000%

    No Known Activations