© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 132189
    Prev
    Next
    INDEX
    Explanations

    commands with package managers

    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_1_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
     a
    1.39
    на
    1.22
     to
    1.19
    ون
    1.14
    ى
    1.11
    ne
    1.04
    ↵↵
    1.01
    কে
    0.98
     an
    0.97
    ాన్ని
    0.96
    POSITIVE LOGITS
    <h4>
    1.46
    '
    1.42
    ’”
    1.25
    <h3>
    1.16
    AR
    1.08
    '[
    1.08
    <h2>
    1.07
    یک
    1.07
    <h5>
    1.05
    RAC
    1.04
    Activations Density 0.001%

    No Known Activations