© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 175608
    Prev
    Next
    INDEX
    Explanations

    pirates and bandits

    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_20_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
    ági
    0.48
     samano
    0.47
    拨
    0.47
    naf
    0.45
    unar
    0.44
    seti
    0.44
    udahan
    0.44
    棪
    0.44
    Hari
    0.42
    Dst
    0.42
    POSITIVE LOGITS
    α
    0.46
    |^{\
    0.43
     α
    0.42
     للإ
    0.42
     ან
    0.41
    แก้
    0.41
     bevorzug
    0.41
     recours
    0.40
     Cache
    0.40
    自身の
    0.40
    Activations Density 0.002%

    No Known Activations