© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 47943
    Prev
    Next
    INDEX
    Explanations

    keinen access

    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_10_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
     gels
    0.56
     ان
    0.53
     sockets
    0.51
     semi
    0.50
     ions
    0.50
     dryers
    0.49
     circuitos
    0.49
     س
    0.48
     ص
    0.48
     raff
    0.47
    POSITIVE LOGITS
     стандарт
    0.47
    äll
    0.46
    alyse
    0.45
     Emerg
    0.45
     станда
    0.45
     объект
    0.44
    యు
    0.44
     isti
    0.44
     Srbiji
    0.43
    🐟
    0.43
    Activations Density 0.000%

    No Known Activations