© 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. 157508
    Prev
    Next
    INDEX
    Explanations

    Roku devices and channels

    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
    น
    1.43
    ت
    1.38
    ת
    1.34
    ע
    1.34
    عنی
    1.33
    at
    1.30
    ির
    1.26
    та
    1.24
    {
    1.22
    ur
    1.20
    POSITIVE LOGITS
    ني
    1.24
    。）
    1.18
    ler
    1.10
    ли
    1.06
    。
    1.06
    1.03
     (
    1.01
    ）
    0.98
    ۔
    0.97
    在
    0.91
    Activations Density 0.001%

    No Known Activations