© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 131794
    Prev
    Next
    INDEX
    Explanations

    Dutch language

    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_50_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
    🄴
    0.47
    PEM
    0.44
    🅔
    0.42
     PEM
    0.41
    ERE
    0.41
     ere
    0.41
    世紀
    0.41
    蜂
    0.40
     tere
    0.40
    ாந்து
    0.40
    POSITIVE LOGITS
    pr
    0.51
     pr
    0.46
     kie
    0.45
     пра
    0.41
    かう
    0.41
     окра
    0.40
     Ladd
    0.40
     pra
    0.39
    bal
    0.38
    Pr
    0.38
    Activations Density 0.001%

    No Known Activations