© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 88424
    Prev
    Next
    INDEX
    Explanations

    Anna names and associated context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_3_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
     komunikasi
    0.79
    を取得
    0.78
    가
    0.77
    로
    0.76
    를
    0.73
     njegov
    0.71
    が
    0.71
    𝗻
    0.68
    𝗴
    0.68
     pengertian
    0.66
    POSITIVE LOGITS
    </h2>
    0.62
    ం
    0.59
     beaded
    0.58
    </h1>
    0.57
    </h3>
    0.57
     Artemis
    0.57
     An
    0.55
    ሦ
    0.55
     ruby
    0.54
     Sapphire
    0.54
    Activations Density 0.000%

    No Known Activations