© 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. 126527
    Prev
    Next
    INDEX
    Explanations

    zirconia, uju, phase, cucumbers

    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
     for
    0.92
    ’
    0.88
    '
    0.87
    𝚣
    0.86
     of
    0.77
    𝔀
    0.73
    י
    0.73
    𝚟
    0.73
    weight
    0.70
    𝐳
    0.70
    POSITIVE LOGITS
    as
    0.63
    ing
    0.62
    un
    0.60
     व
    0.59
    ็ง
    0.58
    이었
    0.57
    दछ
    0.55
     tapestry
    0.55
    า
    0.55
    WithObjects
    0.52
    Activations Density 0.001%

    No Known Activations