© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    4. 104594
    Prev
    Next
    INDEX
    Explanations

    LCD display

    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_44_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
     black
    0.37
    液晶
    0.36
    실
    0.36
    黒
    0.36
    реа
    0.35
    displayed
    0.35
    display
    0.35
     display
    0.35
     %=
    0.35
    black
    0.34
    POSITIVE LOGITS
     BOU
    0.42
    笥
    0.40
     Intelig
    0.38
     Bingham
    0.38
    Steps
    0.38
     Intelligen
    0.37
    TempVal
    0.37
    asets
    0.36
     bxa
    0.36
     Kagan
    0.36
    Activations Density 0.002%

    No Known Activations