© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 45580
    Prev
    Next
    INDEX
    Explanations

    text rephrasing suggestions

    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_22_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
     intrav
    0.29
    Harper
    0.27
     interracial
    0.27
     nanny
    0.27
    delà
    0.26
     voy
    0.24
    ्यूस
    0.23
    ｈ
    0.23
     southbound
    0.23
     теат
    0.23
    POSITIVE LOGITS
     கல்வி
    0.27
    wasm
    0.24
     পূরণ
    0.23
    >\<^
    0.23
    كنولوج
    0.23
     Calculate
    0.23
    なります
    0.23
     Remove
    0.23
     olho
    0.23
     ચો
    0.23
    Activations Density 0.027%

    No Known Activations