© 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. 81262
    Prev
    Next
    INDEX
    Explanations

    D

    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
    ianos
    0.41
    ់
    0.39
     किशन
    0.38
    लान
    0.37
    *{-
    0.36
    iamine
    0.36
    pasar
    0.36
    lav
    0.35
     anda
    0.35
    msen
    0.35
    POSITIVE LOGITS
    ንግ
    0.48
    江
    0.38
    ิทธิ
    0.38
     j
    0.38
    荏
    0.38
     Jordan
    0.37
     JMJD
    0.37
    秘
    0.37
     реги
    0.36
    Jordan
    0.36
    Activations Density 0.011%

    No Known Activations