© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    4. 204064
    Prev
    Next
    INDEX
    Explanations

    state

    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
    及
    0.43
    oler
    0.37
    venth
    0.36
     Cent
    0.36
    iological
    0.36
     place
    0.35
     exact
    0.35
    ൃത്ത
    0.35
    ruit
    0.34
    ponsorship
    0.34
    POSITIVE LOGITS
     guineas
    0.40
    вни
    0.38
    ्स
    0.37
    二
    0.35
    上线
    0.35
    ப்புகளை
    0.35
    ).*
    0.35
    ዱ
    0.35
    สัญญาณ
    0.34
    immungen
    0.34
    Activations Density 0.003%

    No Known Activations