© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 110795
    Prev
    Next
    INDEX
    Explanations

    come forward with

    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
    t
    1.64
    ون
    1.27
    í
    1.22
    v
    1.19
    ik
    1.13
    g
    1.06
    et
    1.01
    ت
    1.01
     It
    0.99
    ü
    0.99
    POSITIVE LOGITS
    ın
    1.06
    Cantidad
    1.03
    )’
    1.00
    ك
    0.97
    )：
    0.94
    น
    0.94
    in
    0.93
    ,
    0.92
    ین
    0.91
    де
    0.91
    Activations Density 0.002%

    No Known Activations