© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 10902
    Prev
    Next
    INDEX
    Explanations

    wood and building materials

    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
     be
    0.49
    ーム
    0.44
    би
    0.43
    -
    0.42
    ерт
    0.41
    чен
    0.39
    }
    0.38
    אם
    0.38
    ડિયો
    0.38
     Chong
    0.38
    POSITIVE LOGITS
     Wood
    0.45
     Saw
    0.41
    <0x0D>
    0.41
     Backbone
    0.41
     लकड़ी
    0.40
     Forest
    0.40
     ਤ
    0.40
     Carrot
    0.40
     nouvelle
    0.40
     madeira
    0.39
    Activations Density 0.064%

    No Known Activations