© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 39253
    Prev
    Next
    INDEX
    Explanations

    America First

    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
    as
    1.20
    م
    0.93
     on
    0.91
    ك
    0.90
    ed
    0.90
    ש
    0.89
    ت
    0.85
    et
    0.84
    an
    0.82
    er
    0.81
    POSITIVE LOGITS
    ও
    0.71
     îng
    0.67
    واء
    0.64
     تعلیم
    0.64
    ِی
    0.63
    ꒪
    0.61
    体の
    0.60
     krwi
    0.59
    ینه
    0.59
    ͜
    0.59
    Activations Density 0.003%

    No Known Activations