© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 140129
    Prev
    Next
    INDEX
    Explanations

    conversely followed by word or comma

    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_12_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
    эд
    0.35
     pajamas
    0.35
    們
    0.34
    मपुर
    0.33
     mať
    0.33
     dictators
    0.32
    𝟬
    0.32
     apoyo
    0.32
     curtailed
    0.32
     curvatures
    0.32
    POSITIVE LOGITS
    ס
    0.46
    arc
    0.44
    a
    0.37
    However
    0.37
    BA
    0.36
    с
    0.36
    c
    0.36
    ag
    0.35
    ap
    0.35
    boyfriend
    0.35
    Activations Density 0.001%

    No Known Activations