© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 172055
    Prev
    Next
    INDEX
    Explanations

    of the

    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_20_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
    SecurityMarks
    0.32
     krank
    0.29
    umeric
    0.29
     Initiatives
    0.29
     आवर
    0.29
     patriot
    0.28
    ў
    0.28
    éric
    0.28
    mage
    0.28
     أول
    0.28
    POSITIVE LOGITS
     gusto
    0.28
    </em>
    0.27
     buddy
    0.27
     neighbour
    0.26
    သိ
    0.26
    Ter
    0.26
    Gust
    0.26
     watchdog
    0.26
    Toxic
    0.26
    P
    0.26
    Activations Density 0.004%

    No Known Activations