© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 76690
    Prev
    Next
    INDEX
    Explanations

    #include statements

    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_31_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
    槳
    0.23
     PUN
    0.23
     pun
    0.23
     RS
    0.23
     exhaust
    0.22
     CONCEPT
    0.22
     synonym
    0.21
     verl
    0.21
     det
    0.20
     Verl
    0.20
    POSITIVE LOGITS
    Localization
    0.24
    Dor
    0.23
    Decorative
    0.23
     لق
    0.23
    蒨
    0.23
     درون
    0.22
     День
    0.22
    Địa
    0.22
    汴
    0.22
    🇭
    0.22
    Activations Density 0.001%

    No Known Activations