© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 9763
    Prev
    Next
    INDEX
    Explanations

    leafy greens

    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_13_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
    Guitar
    0.52
    guitar
    0.48
    disk
    0.47
    cod
    0.46
    歯
    0.46
    acoustic
    0.45
    रू
    0.45
    ギター
    0.45
    prä
    0.45
    ゴム
    0.44
    POSITIVE LOGITS
    蔬菜
    0.59
     zucchini
    0.58
     leafy
    0.52
    🥬
    0.51
     importância
    0.50
    强调
    0.50
    公示
    0.50
     sottoline
    0.50
     herbs
    0.49
     vegetable
    0.49
    Activations Density 0.008%

    No Known Activations