© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 13557
    Prev
    Next
    INDEX
    Explanations

    adult, pediatric, presidential

    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
    WithOptions
    0.37
    relsen
    0.36
    gled
    0.34
    믹
    0.34
    Profes
    0.34
    드의
    0.34
    Interpretation
    0.33
     infantil
    0.33
    路由
    0.33
    方の
    0.33
    POSITIVE LOGITS
    _*
    0.41
     {"
    0.40
    asche
    0.39
    襪
    0.38
     Departments
    0.38
    용
    0.38
    wear
    0.37
     അത്
    0.36
    _"
    0.36
     osu
    0.36
    Activations Density 0.053%

    No Known Activations