© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 149899
    Prev
    Next
    INDEX
    Explanations

    original, pre, normal, baseline, price

    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_18_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
    nails
    0.47
    絣
    0.45
     wheels
    0.42
     şek
    0.42
    acr
    0.42
    oons
    0.42
    arski
    0.41
    ized
    0.41
    icio
    0.41
     decks
    0.41
    POSITIVE LOGITS
    λαμβ
    0.54
    Î
    0.50
    Observe
    0.47
     روز
    0.45
     observe
    0.45
     prendere
    0.44
    ョ
    0.44
    観察
    0.44
     normale
    0.44
    γν
    0.44
    Activations Density 0.017%

    No Known Activations