© 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. 112259
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ی
    1.03
    4
    1.01
    ,
    0.98
    де
    0.92
    ни
    0.92
    ("
    0.91
    й
    0.91
    5
    0.89
    ۴
    0.88
    iril
    0.85
    POSITIVE LOGITS
    t
    1.45
    ات
    1.31
    n
    1.16
    л
    1.11
    ת
    1.11
    ية
    1.08
    。
    1.03
    ant
    0.98
    w
    0.98
    ט
    0.98
    Activations Density 0.000%

    No Known Activations