© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 33702
    Prev
    Next
    INDEX
    Explanations

    unit areacircle

    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_3_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
     on
    0.72
    л
    0.70
    是
    0.68
    ৫
    0.64
    اً
    0.63
    ير
    0.62
    اه
    0.61
    는
    0.60
    埛
    0.59
    وم
    0.59
    POSITIVE LOGITS
     deci
    0.69
     convicts
    0.68
     installs
    0.67
    ຂໍ້ມ
    0.66
    AT
    0.65
     unit
    0.63
    ece
    0.63
    ຜະລິດຕ
    0.62
     barring
    0.62
    ant
    0.61
    Activations Density 0.006%

    No Known Activations