© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 68127
    Prev
    Next
    INDEX
    Explanations

    join

    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
    ệ
    0.37
    positroids
    0.35
    ኵ
    0.35
     bhij
    0.34
    йин
    0.33
    gae
    0.33
     cron
    0.33
    鵰
    0.33
    gqlgen
    0.32
     கிட
    0.32
    POSITIVE LOGITS
     joined
    3.39
     join
    3.38
     Join
    3.22
    Join
    3.19
     joining
    3.16
    join
    3.14
     joins
    3.13
     Joining
    3.11
    joined
    3.03
     Joined
    3.03
    Activations Density 0.120%

    No Known Activations