© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 15218
    Prev
    Next
    INDEX
    Explanations

    crafting tools and items

    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_40_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
    Sequ
    0.42
    Level
    0.41
    level
    0.39
    RQ
    0.39
    곱
    0.39
    Sides
    0.38
     '*
    0.38
    chow
    0.38
    eney
    0.38
    LEVEL
    0.37
    POSITIVE LOGITS
     Ing
    0.48
     ingot
    0.44
     ing
    0.43
     crude
    0.43
     tools
    0.42
     ingredients
    0.42
     ore
    0.42
     blocks
    0.41
    锭
    0.41
     Ore
    0.41
    Activations Density 0.023%

    No Known Activations