© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 234369
    Prev
    Next
    INDEX
    Explanations

    code or technical terms

    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_46_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
    グリ
    0.42
     Puck
    0.37
     subsystem
    0.36
     Substances
    0.36
     WIFI
    0.36
    itza
    0.35
    gly
    0.35
    ²)
    0.35
     p
    0.35
    ওয়
    0.35
    POSITIVE LOGITS
    tım
    0.40
    Қ
    0.38
    ⏜
    0.38
     nominate
    0.38
    läger
    0.38
     utter
    0.37
     parenthesis
    0.37
    ucional
    0.37
    ٹے
    0.37
     bancos
    0.37
    Activations Density 0.000%

    No Known Activations