© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 150892
    Prev
    Next
    INDEX
    Explanations

    units of length

    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_23_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
     types
    0.40
     worst
    0.40
     maths
    0.39
    Gamepad
    0.39
     mathematics
    0.38
    :\/\/
    0.38
     کردار
    0.38
     emperor
    0.37
     komputer
    0.37
     prehistoric
    0.37
    POSITIVE LOGITS
    лли
    0.47
    бира
    0.45
    苡
    0.44
     따라
    0.42
    псо
    0.42
    шру
    0.41
    ванный
    0.40
     Talia
    0.39
    READER
    0.39
    bri
    0.39
    Activations Density 0.002%

    No Known Activations