© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 2413
    Prev
    Next
    INDEX
    Explanations

    bees and honey

    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_39_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
    ⭒
    0.41
     Spinach
    0.41
     spinach
    0.36
    Julia
    0.36
     рыб
    0.35
     ikan
    0.35
     arroz
    0.34
    魚
    0.34
     Bian
    0.33
     किरण
    0.33
    POSITIVE LOGITS
     hive
    1.73
     hives
    1.62
    蜂
    1.56
     honey
    1.55
     Hive
    1.50
     bees
    1.49
     bee
    1.48
    🐝
    1.48
     beeh
    1.42
     Honey
    1.41
    Activations Density 0.076%

    No Known Activations