© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 110019
    Prev
    Next
    INDEX
    Explanations

    release of endorphins

    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_2_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
    0.99
    s
    0.92
    voting
    0.91
    problem
    0.85
    ᆸ
    0.84
    ی
    0.84
    year
    0.84
    ann
    0.83
    planning
    0.82
    vis
    0.82
    POSITIVE LOGITS
    ו
    1.55
    ת
    1.41
    ী
    1.20
    ف
    1.15
    l
    1.14
    ある
    1.11
    ע
    1.04
     anciens
    0.98
    תה
    0.96
    את
    0.95
    Activations Density 0.000%

    No Known Activations