© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 151596
    Prev
    Next
    INDEX
    Explanations

    steel

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_60_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
    for
    0.48
    fee
    0.45
    ليه
    0.41
    гло
    0.41
    FOR
    0.40
    fil
    0.40
    f
    0.40
    ფ
    0.39
    Blue
    0.39
    fte
    0.38
    POSITIVE LOGITS
    wide
    0.75
    wan
    0.70
    working
    0.64
    wał
    0.63
    wać
    0.62
    wie
    0.61
    waard
    0.61
    way
    0.61
    wa
    0.60
    wani
    0.60
    Activations Density 0.001%

    No Known Activations