© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 245188
    Prev
    Next
    INDEX
    Explanations

    HTML parsing BeautifulSoup

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_40_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
    Need
    0.41
    Gr
    0.40
     SR
    0.39
     Escape
    0.38
    Trans
    0.38
     Deg
    0.38
    Still
    0.37
    阝
    0.37
    Scha
    0.36
    ward
    0.36
    POSITIVE LOGITS
    चालित
    0.40
     mely
    0.39
     nedeni
    0.39
     consecutivos
    0.39
     jóvenes
    0.39
    ulosic
    0.37
     pensato
    0.37
    instances
    0.37
     sebebi
    0.37
     Akhtar
    0.37
    Activations Density 0.002%

    No Known Activations