© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 62236
    Prev
    Next
    INDEX
    Explanations

    should not

    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
    т
    1.20
    ก
    1.20
     ocho
    1.00
    กิน
    0.91
     aumentar
    0.89
     an
    0.87
     jap
    0.87
    هم
    0.87
     cerve
    0.86
     atteindre
    0.86
    POSITIVE LOGITS
    q
    0.99
    स
    0.97
    सँग
    0.87
    ud
    0.85
    ি
    0.85
    f
    0.84
    ু
    0.79
    o
    0.75
    2
    0.75
    i
    0.74
    Activations Density 0.001%

    No Known Activations