© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 221568
    Prev
    Next
    INDEX
    Explanations

    really followed by adjective/verb

    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_10_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
    ز
    0.94
    ER
    0.89
     a
    0.86
    اه
    0.84
    ok
    0.82
    اول
    0.80
    od
    0.80
     t
    0.78
    ist
    0.77
    un
    0.77
    POSITIVE LOGITS
    ли
    0.83
    㿟
    0.75
    徃
    0.73
    üren
    0.71
     depósito
    0.71
    lç
    0.70
     Studium
    0.70
    蜢
    0.69
    样式
    0.68
    䄪
    0.68
    Activations Density 0.004%

    No Known Activations