© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 45376
    Prev
    Next
    INDEX
    Explanations

    can you believe

    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_13_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
     mức
    0.51
     ‚
    0.49
     Scientology
    0.49
    followlike
    0.49
    </strong>
    0.47
    abouts
    0.47
    rün
    0.47
     स्‍टार
    0.47
    ças
    0.46
    𝟎
    0.46
    POSITIVE LOGITS
    (
    0.65
    {
    0.50
    ണ്ഡ
    0.46
    (“
    0.45
     laag
    0.45
    อร์
    0.42
    Fabric
    0.42
    Czas
    0.42
    Height
    0.42
     (“
    0.42
    Activations Density 0.000%

    No Known Activations