© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 101985
    Prev
    Next
    INDEX
    Explanations

    data and classification

    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_14_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
    रन
    0.54
     plotted
    0.51
     extinguished
    0.51
    </td>
    0.50
    واء
    0.50
     obstructing
    0.50
     steepest
    0.50
    搧
    0.48
     impeded
    0.48
     stipulated
    0.48
    POSITIVE LOGITS
     G
    0.58
    dato
    0.57
    child
    0.57
     মতে
    0.57
    data
    0.55
    dynamics
    0.55
    dynamic
    0.54
     жить
    0.54
    parent
    0.53
    digital
    0.53
    Activations Density 0.000%

    No Known Activations