© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 133553
    Prev
    Next
    INDEX
    Explanations

    foreign words and phrases

    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_6_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
    л
    1.12
    ons
    0.92
    ق
    0.91
    ل
    0.88
    and
    0.87
    Z
    0.86
    ške
    0.86
    вих
    0.86
    with
    0.85
    Then
    0.85
    POSITIVE LOGITS
     of
    1.22
    m
    1.16
     เข
    1.10
     dobry
    1.04
     kunnen
    1.02
     OF
    1.01
     แค
    1.01
     บ
    1.00
     nghe
    1.00
     był
    1.00
    Activations Density 0.003%

    No Known Activations