© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 104603
    Prev
    Next
    INDEX
    Explanations

    cottonmouth

    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_1_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
    2
    1.08
     for
    1.06
    دأ
    0.95
     enormously
    0.92
    ts
    0.90
    什么
    0.90
     poč
    0.89
    test
    0.88
    د
    0.88
    rául
    0.88
    POSITIVE LOGITS
    ı
    1.58
    {
    1.51
    т
    1.50
    í
    1.39
    </strong>
    1.36
    ة
    1.36
    ے
    1.35
    ం
    1.32
    й
    1.30
    ์
    1.24
    Activations Density 0.001%

    No Known Activations