© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 226305
    Prev
    Next
    INDEX
    Explanations

    straits, bays, channels, inlets

    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_10_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
    en
    0.88
    es
    0.80
    e
    0.71
    sudo
    0.68
    essed
    0.65
    امة
    0.62
    enan
    0.61
    ۹
    0.61
     কাবুল
    0.60
     bein
    0.60
    POSITIVE LOGITS
    ై
    0.80
    ний
    0.73
    PACT
    0.69
    า
    0.69
    ல்
    0.68
    ো
    0.61
     Cộng
    0.59
    ITAS
    0.59
    ITIS
    0.59
    ೊ
    0.59
    Activations Density 0.003%

    No Known Activations