© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 108662
    Prev
    Next
    INDEX
    Explanations

    Dutch 'eft' / 'ven' words

    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_2_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
    ))
    1.08
    도
    1.05
    も
    0.98
    માં
    0.94
     in
    0.93
    로
    0.92
    在
    0.88
     reorgan
    0.87
    ও
    0.87
    )),
    0.86
    POSITIVE LOGITS
    is
    1.52
    ли
    1.52
    é
    1.48
     It
    1.41
    í
    1.35
    f
    1.34
    ار
    1.30
    t
    1.27
    ری
    1.23
    ون
    1.22
    Activations Density 0.000%

    No Known Activations