© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 159392
    Prev
    Next
    INDEX
    Explanations

    Dutch language markers

    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
    ون
    1.35
    న
    1.33
    as
    1.32
    er
    1.24
    ému
    1.24
    ا
    1.22
    in
    1.19
    ن
    1.13
    h
    1.12
    an
    1.10
    POSITIVE LOGITS
    ो
    1.16
    ３
    1.13
    دی
    1.07
     ३
    1.06
     لی
    1.05
    کار
    1.04
     था
    1.02
    のは
    1.02
    ぎ
    1.02
     जो
    1.01
    Activations Density 0.000%

    No Known Activations