© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 45517
    Prev
    Next
    INDEX
    Explanations

    cell proliferation

    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_13_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
    CurrentImageData
    0.62
     ब
    0.60
     ב
    0.59
     ק
    0.57
     מ
    0.55
     ക
    0.54
     bitcoin
    0.54
    ی
    0.54
    謃
    0.53
     ک
    0.52
    POSITIVE LOGITS
    R
    0.54
    Flower
    0.53
    RO
    0.52
    han
    0.51
    educt
    0.51
    تاب
    0.50
    হইল
    0.50
     Flower
    0.49
    RAJ
    0.49
    xrightarrow
    0.49
    Activations Density 0.013%

    No Known Activations