© 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. 123037
    Prev
    Next
    INDEX
    Explanations

    instructional design or Luis Borges

    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
     It
    1.05
     They
    0.76
    s
    0.73
    с
    0.73
     This
    0.65
    </h2>
    0.63
    ับ
    0.63
    salary
    0.62
    </span>
    0.61
     If
    0.61
    POSITIVE LOGITS
    ي
    0.83
    ק
    0.81
    י
    0.81
    ج
    0.77
    ע
    0.74
     oppure
    0.73
    i
    0.71
    x
    0.70
    ant
    0.68
    იკ
    0.68
    Activations Density 0.000%

    No Known Activations