© 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. 77951
    Prev
    Next
    INDEX
    Explanations

    Zoo and Hospital

    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
    bure
    0.39
     eosin
    0.37
     aureus
    0.36
     sal
    0.35
    ﺛ
    0.35
     لأنه
    0.35
    ということは
    0.35
     Bells
    0.34
    綿
    0.34
     Rhod
    0.34
    POSITIVE LOGITS
     d
    1.01
     д
    0.76
     د
    0.73
     द
    0.71
    <0x93>
    0.65
     ד
    0.63
     D
    0.57
     h
    0.56
    ด
    0.50
    d
    0.49
    Activations Density 0.008%

    No Known Activations