© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 89782
    Prev
    Next
    INDEX
    Explanations

    word endings like "-en", "-ed", "-ern"

    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_18_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
     marít
    0.52
     littoral
    0.51
    高铁
    0.49
    ي
    0.49
     ASGI
    0.48
     މ
    0.47
     shumë
    0.47
     werewolf
    0.47
     marrón
    0.47
     evidentiary
    0.46
    POSITIVE LOGITS
    ene
    0.60
    ern
    0.58
    ill
    0.54
    ods
    0.52
    ers
    0.51
    eds
    0.51
    ate
    0.51
    ances
    0.51
    1
    0.51
    enos
    0.50
    Activations Density 0.000%

    No Known Activations