© 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. 79002
    Prev
    Next
    INDEX
    Explanations

    names and specific terms

    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
    ెర
    0.44
     гиб
    0.41
     রাখেন
    0.39
    λω
    0.38
    驿
    0.37
    horns
    0.36
    রক্ষ
    0.35
    灵活
    0.35
    Bats
    0.35
     ввод
    0.35
    POSITIVE LOGITS
    obium
    0.44
     Thane
    0.39
    帑
    0.38
     Kxe
    0.38
     Пра
    0.36
     mayam
    0.36
    𝘰
    0.36
    óstico
    0.36
     competencies
    0.36
    adow
    0.36
    Activations Density 0.000%

    No Known Activations