© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 79043
    Prev
    Next
    INDEX
    Explanations

    T

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_53_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
    ዶች
    0.42
    trail
    0.40
    Trail
    0.38
    溽
    0.38
    shear
    0.36
     Trail
    0.36
     Kup
    0.35
     trail
    0.35
    쳤
    0.35
    mam
    0.34
    POSITIVE LOGITS
     T
    2.06
     t
    1.63
    T
    1.52
     Т
    1.40
     الت
    1.22
    Ｔ
    1.20
     ت
    1.16
     त
    1.13
     Τ
    1.10
     टी
    1.09
    Activations Density 0.004%

    No Known Activations