© 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. 142085
    Prev
    Next
    INDEX
    Explanations

    If

    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
     holen
    0.39
     işlem
    0.38
    Train
    0.38
     बजाज
    0.38
    loan
    0.38
     죄
    0.37
     given
    0.37
    Hourly
    0.37
    use
    0.37
    given
    0.36
    POSITIVE LOGITS
     виконав
    0.41
    就不
    0.37
    initComponents
    0.35
     Whoever
    0.35
     ارشاد
    0.34
     LU
    0.33
    денти
    0.33
     应
    0.33
     geh
    0.32
    戸
    0.32
    Activations Density 0.006%

    No Known Activations