© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 918
    Prev
    Next
    INDEX
    Explanations

    you can find more information

    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_40_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
     follows
    0.44
     नोंद
    0.40
     folgt
    0.37
     Domain
    0.37
    ഘാ
    0.35
     Request
    0.35
    兆
    0.35
     request
    0.35
     那麼
    0.35
     acted
    0.34
    POSITIVE LOGITS
     люди
    0.40
    People
    0.39
    ᴺ
    0.39
    琵
    0.38
    样子
    0.38
     people
    0.38
    Bine
    0.37
    itiv
    0.36
    Интернет
    0.36
     Californians
    0.35
    Activations Density 0.020%

    No Known Activations