© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 43056
    Prev
    Next
    INDEX
    Explanations

    Great Barrier Reef and restaurants

    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_3_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
    ت
    0.66
    ெ
    0.60
     август
    0.58
    ek
    0.57
    迤
    0.57
    <0x96>
    0.56
    <0xAD>
    0.55
     fler
    0.54
     for
    0.53
    are
    0.53
    POSITIVE LOGITS
     on
    0.84
    ها
    0.83
    ции
    0.83
    お
    0.77
     southern
    0.74
    r
    0.72
    になる
    0.71
    する
    0.70
    ので
    0.69
    ني
    0.69
    Activations Density 0.001%

    No Known Activations