© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 81726
    Prev
    Next
    INDEX
    Explanations

    text fragments

    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
     E
    0.45
     treasure
    0.43
    ებზე
    0.42
     Tö
    0.41
     tô
    0.40
    āja
    0.40
     Bir
    0.38
     toll
    0.38
     tule
    0.38
     Treasure
    0.38
    POSITIVE LOGITS
    Buzz
    0.39
    lly
    0.39
    𝙢
    0.37
    ूम
    0.37
     malesuada
    0.36
     મહિ
    0.36
    ोगी
    0.36
    Ꮇ
    0.36
    apeti
    0.35
    ificat
    0.35
    Activations Density 0.000%

    No Known Activations