© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 38094
    Prev
    Next
    INDEX
    Explanations

    nowhere near

    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_11_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
    Converting
    0.61
     Selecting
    0.60
     अनुभवी
    0.59
    Perhaps
    0.58
     Consulting
    0.57
     Configuring
    0.57
    .??.??"]
    0.57
    '$,
    0.56
    phants
    0.55
    +]
    0.54
    POSITIVE LOGITS
    ले
    0.63
    <h3>
    0.61
    lend
    0.59
     biofilms
    0.58
     Langer
    0.56
    '
    0.56
     oprac
    0.55
     elenc
    0.54
     cinética
    0.53
    ల
    0.53
    Activations Density 0.003%

    No Known Activations