© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 35727
    Prev
    Next
    INDEX
    Explanations

    of/de + noun phrase

    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_3_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
    ↵
    0.91
     or
    0.76
    ia
    0.74
     as
    0.73
     city
    0.73
     popup
    0.69
    0
    0.69
     style
    0.68
     ville
    0.68
    as
    0.68
    POSITIVE LOGITS
    tions
    1.23
    tion
    1.18
    sion
    1.17
    ITION
    1.01
    ación
    0.96
    rection
    0.95
    traction
    0.95
    ーション
    0.95
    r
    0.95
    b
    0.95
    Activations Density 0.178%

    No Known Activations