© 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-3-4B-IT
    5. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 9614
    Prev
    Next
    INDEX
    Explanations

    MVC pattern

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_25_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
     item
    0.68
     master
    0.67
    ý
    0.63
    नाक
    0.63
     Namespace
    0.62
    നു
    0.61
     জাতিকে
    0.61
     적
    0.60
    TASK
    0.60
    제품
    0.60
    POSITIVE LOGITS
    mybatis
    0.68
     hess
    0.67
     удиви
    0.66
     Poo
    0.65
    logic
    0.65
    ίο
    0.64
    mLogin
    0.63
     Logic
    0.63
    サー
    0.63
     Hospital
    0.62
    Activations Density 0.007%

    No Known Activations