© 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. 82402
    Prev
    Next
    INDEX
    Explanations

    places

    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
     O
    0.44
    산
    0.41
     Journals
    0.38
    산을
    0.37
     Col
    0.35
    San
    0.35
     Par
    0.34
     Mar
    0.34
    istles
    0.34
    igos
    0.34
    POSITIVE LOGITS
    tar
    0.41
     kred
    0.41
     Elise
    0.39
    ሏ
    0.39
    Her
    0.39
    tare
    0.39
    тэ
    0.39
     Her
    0.39
     Tare
    0.39
     Leonid
    0.39
    Activations Density 0.003%

    No Known Activations