© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 136646
    Prev
    Next
    INDEX
    Explanations

    data structures and programming concepts

    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_37_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
     mim
    0.39
    ადა
    0.38
    榄
    0.38
     vess
    0.38
     Fitzpatrick
    0.37
    Thought
    0.36
    okk
    0.36
     Hr
    0.36
    潾
    0.36
    multipart
    0.36
    POSITIVE LOGITS
     ನಗರ
    0.38
     Remix
    0.37
     град
    0.37
    ViewModel
    0.35
     Государ
    0.35
     внима
    0.35
    नगर
    0.35
     deserves
    0.34
     уде
    0.34
     Employees
    0.34
    Activations Density 0.000%

    No Known Activations