© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 107389
    Prev
    Next
    INDEX
    Explanations

    motivation for action

    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_2_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
    ன்
    1.41
    did
    1.21
    for
    1.20
     большая
    1.13
    ꞎ
    1.13
    the
    1.07
     بیماری
    1.05
    ன்ஸ்
    1.05
    ності
    1.04
    pubescens
    1.04
    POSITIVE LOGITS
     a
    1.59
    ני
    1.52
     is
    1.42
    ية
    1.40
    </h2>
    1.38
    לי
    1.38
    <0x0D>
    1.33
    1
    1.29
     to
    1.24
    是
    1.23
    Activations Density 0.003%

    No Known Activations