© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 168833
    Prev
    Next
    INDEX
    Explanations

    taxes

    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_56_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
     tax
    1.70
    tax
    1.56
     Tax
    1.55
    Tax
    1.50
     налого
    1.23
    税
    1.23
     TAX
    1.21
     टैक्स
    1.13
    TAX
    1.10
    稅
    1.08
    POSITIVE LOGITS
     قابل
    0.49
     adjustable
    0.47
    adjustable
    0.44
     ಅನ್ನ
    0.43
     unbreakable
    0.42
    wrist
    0.42
    永久
    0.42
     modific
    0.41
     modificar
    0.40
    قابل
    0.40
    Activations Density 0.001%

    No Known Activations