© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 100412
    Prev
    Next
    INDEX
    Explanations

    1788 ratification federal states

    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_14_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
     rever
    0.52
    מור
    0.51
     delim
    0.50
     Objection
    0.48
     delimited
    0.47
    מוש
    0.47
    Experiment
    0.47
    {
    0.47
    아요
    0.46
    Query
    0.46
    POSITIVE LOGITS
     மாநிலத்தில்
    0.62
    ಿಗಳ
    0.58
     ਰਾ
    0.57
    𝗦
    0.56
    ্টে
    0.55
     дзяржа
    0.55
    ό
    0.55
     ምን
    0.55
     चैन
    0.55
    schod
    0.55
    Activations Density 0.002%

    No Known Activations