© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 162371
    Prev
    Next
    INDEX
    Explanations

    versions and libraries

    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_31_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
    incoming
    0.33
    Outgoing
    0.32
    𝑈
    0.32
    摂取
    0.30
     Incoming
    0.30
    𝐺
    0.30
     थोड़ी
    0.29
     भूत
    0.29
     श्रीलंका
    0.29
    ట్లో
    0.29
    POSITIVE LOGITS
     kusal
    0.31
     crush
    0.30
    ราง
    0.29
     Cong
    0.29
    Xin
    0.28
    ymas
    0.28
    渡
    0.28
    ោង
    0.27
    xes
    0.27
     degeneration
    0.26
    Activations Density 0.004%

    No Known Activations