© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 151108
    Prev
    Next
    INDEX
    Explanations

    CS business 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_60_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
    ﺘ
    0.42
    лни
    0.41
    یک
    0.41
     giving
    0.40
    ИТ
    0.40
    িক
    0.39
     particular
    0.39
     stal
    0.38
    ۔
    0.38
    IPPING
    0.38
    POSITIVE LOGITS
    z
    0.52
    kaj
    0.46
    hij
    0.44
    zai
    0.43
    u
    0.43
    ska
    0.42
    </a>
    0.42
    zahlen
    0.42
    av
    0.42
    baby
    0.41
    Activations Density 0.000%

    No Known Activations