© 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. 9358
    Prev
    Next
    INDEX
    Explanations

    creating new projects

    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
    납
    0.75
     announcements
    0.73
     confirmer
    0.67
     जमीन
    0.66
    shape
    0.66
    OPEN
    0.65
    orbit
    0.64
    builder
    0.64
    रासायनिक
    0.64
     potvr
    0.62
    POSITIVE LOGITS
     научных
    0.69
    祿
    0.69
     vucc
    0.69
    elligent
    0.68
    скую
    0.68
     scanf
    0.67
     Governors
    0.67
    ский
    0.67
    ಲ್
    0.67
    탬
    0.66
    Activations Density 0.010%

    No Known Activations