© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 204413
    Prev
    Next
    INDEX
    Explanations

    hold or store data

    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_37_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
    彿
    0.39
     भेजी
    0.38
     sing
    0.37
    িগণ
    0.37
     wykony
    0.37
    ளாவ
    0.35
    ujący
    0.34
    送到
    0.34
     करीत
    0.34
    <0xD3>
    0.33
    POSITIVE LOGITS
     host
    0.60
     hosts
    0.59
     hosting
    0.59
    hosts
    0.57
    Hosting
    0.54
    hosting
    0.54
    host
    0.52
     Hosting
    0.51
     मेजब
    0.50
    Hosts
    0.50
    Activations Density 0.006%

    No Known Activations