© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 165163
    Prev
    Next
    INDEX
    Explanations

    a poem, quote, or list

    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_13_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
    ?,?,
    0.47
     kapcsolat
    0.47
    commended
    0.47
     desple
    0.47
    на
    0.46
    path
    0.46
    後
    0.46
    تم
    0.45
     შეგიძლიათ
    0.45
     లు
    0.44
    POSITIVE LOGITS
     Peers
    0.51
     Peer
    0.49
    Vic
    0.47
     Peyton
    0.46
     Passive
    0.44
     Tori
    0.44
     Compression
    0.44
     Eternal
    0.43
     Feminist
    0.43
     Peaks
    0.42
    Activations Density 0.000%

    No Known Activations