© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 17284
    Prev
    Next
    INDEX
    Explanations

    last or end

    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_34_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
    禊
    0.38
     meant
    0.37
     யா
    0.35
     Alfredo
    0.35
    ServiceProvider
    0.35
     Alfred
    0.35
    Alfred
    0.35
    qli
    0.35
     Adriano
    0.35
     sett
    0.34
    POSITIVE LOGITS
     ujung
    0.65
     आखिरी
    0.65
    先端
    0.63
    顶
    0.61
    前端
    0.61
    Послед
    0.61
     posljed
    0.60
     posled
    0.59
    末
    0.59
     last
    0.58
    Activations Density 0.050%

    No Known Activations