© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 126283
    Prev
    Next
    INDEX
    Explanations

    banana bread or boat rides or ads

    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
    ]。
    0.55
    \}.
    0.54
    }$.)
    0.54
    。",
    0.53
    <
    0.52
     toasted
    0.52
    mesi
    0.52
    ir
    0.51
    তেও
    0.51
     avenue
    0.50
    POSITIVE LOGITS
    ت
    0.95
    고
    0.84
    기
    0.73
    ing
    0.71
    т
    0.71
    enes
    0.69
    त
    0.69
    魑
    0.68
    人性
    0.68
    ع
    0.68
    Activations Density 0.000%

    No Known Activations