© 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
    2. Gemma-3-27B-IT
    3. 56-GEMMASCOPE-2-TRANSCODER-262K
    4. 251053
    Prev
    Next
    INDEX
    Explanations

    formal models

    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_56_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
    ifah
    0.37
    FA
    0.36
    넬
    0.36
    㞱
    0.35
     যশোরের
    0.34
    isać
    0.34
    usstsein
    0.34
    കം
    0.33
    捪
    0.33
    uckles
    0.33
    POSITIVE LOGITS
     formal
    0.70
     Formal
    0.65
    Formal
    0.62
     Model
    0.61
    formal
    0.60
    Model
    0.60
     correct
    0.55
     formally
    0.54
     autop
    0.48
     model
    0.45
    Activations Density 0.003%

    No Known Activations