© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 201051
    Prev
    Next
    INDEX
    Explanations

    approaches

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
     사항
    0.38
     തോ
    0.38
     당
    0.37
    虞
    0.37
    俞
    0.37
    themem
    0.36
    ossing
    0.36
    meid
    0.36
    MBOLS
    0.35
     Toch
    0.35
    POSITIVE LOGITS
     approaches
    0.43
     APPROACH
    0.41
    닮
    0.41
     meaning
    0.40
     Approaches
    0.40
    亚太
    0.38
    large
    0.38
     with
    0.38
    dropout
    0.37
     Kuznet
    0.37
    Activations Density 0.003%

    No Known Activations