© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 9018
    Prev
    Next
    INDEX
    Explanations

    proportional to scale or increase

    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_13_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
    ROL
    0.51
    ровень
    0.47
     Tujuan
    0.40
    isions
    0.40
    лк
    0.39
     পুণ
    0.38
    犷
    0.38
    垛
    0.38
     शकतो
    0.37
    ής
    0.37
    POSITIVE LOGITS
    ∗</
    0.35
     נ
    0.34
     Pluto
    0.34
    ﺗ
    0.34
     que
    0.33
     pricey
    0.33
     deacetyl
    0.33
    ت
    0.33
    ତ
    0.33
    祕
    0.33
    Activations Density 0.098%

    No Known Activations