© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 202558
    Prev
    Next
    INDEX
    Explanations

    3D plot design

    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_12_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
     ouvertes
    0.53
    gia
    0.52
    rieg
    0.51
     페
    0.51
    ϳ
    0.49
    ヴァ
    0.49
    rizzle
    0.49
    ڇ
    0.49
     гла
    0.48
    constraintlayout
    0.48
    POSITIVE LOGITS
     we
    0.51
     rescue
    0.48
     minimum
    0.48
     en
    0.48
     tells
    0.47
     establishing
    0.47
    خبر
    0.46
    ான்
    0.46
     rescuing
    0.46
     mountain
    0.46
    Activations Density 0.001%

    No Known Activations