© 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. 204174
    Prev
    Next
    INDEX
    Explanations

    width

    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
    early
    0.38
    Feeling
    0.38
    curses
    0.38
     Constru
    0.36
    基
    0.35
    出售
    0.35
     realising
    0.35
    CDF
    0.34
    阴
    0.34
    conditioning
    0.34
    POSITIVE LOGITS
     eight
    0.42
     registry
    0.40
     mixer
    0.40
    bangan
    0.40
     mannen
    0.39
     BATH
    0.38
    iscope
    0.38
     direkte
    0.37
     Peyton
    0.37
    ေသ
    0.37
    Activations Density 0.000%

    No Known Activations