© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 148430
    Prev
    Next
    INDEX
    Explanations

    In

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_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
     so
    0.42
     via
    0.40
    約
    0.40
    那麼
    0.40
    েত্রে
    0.40
    那么
    0.40
    қда
    0.38
    ﻨ
    0.38
    イタリア
    0.37
    ानीय
    0.37
    POSITIVE LOGITS
     few
    0.59
    few
    0.55
     Few
    0.51
    ve
    0.46
     få
    0.44
    trone
    0.43
    vout
    0.43
    Few
    0.40
     profession
    0.39
     couple
    0.39
    Activations Density 0.000%

    No Known Activations