© 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. 68927
    Prev
    Next
    INDEX
    Explanations

    kind All

    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
    Things
    0.49
     things
    0.48
    things
    0.47
     dingen
    0.46
     cosas
    0.43
     saker
    0.41
    “
    0.41
     Things
    0.40
    柞
    0.40
     ting
    0.38
    POSITIVE LOGITS
     Well
    0.42
    kind
    0.39
     All
    0.39
    χυ
    0.37
     Kind
    0.37
     wells
    0.37
    setMaximum
    0.37
     kind
    0.37
     ऑल
    0.37
    हूर
    0.36
    Activations Density 0.159%

    No Known Activations