© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 239853
    Prev
    Next
    INDEX
    Explanations

    build or style related concepts

    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_25_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
     decorated
    0.44
    AlignedText
    0.42
     Newsletter
    0.41
    ഌ
    0.41
     themed
    0.40
    Rack
    0.40
     figurative
    0.39
     Thì
    0.39
    ="";
    0.39
    TGFuZ
    0.38
    POSITIVE LOGITS
     antib
    0.45
    CHK
    0.41
    чная
    0.39
     главный
    0.38
     duração
    0.38
    信号
    0.36
     ba
    0.35
     distância
    0.35
     incênd
    0.34
     единственный
    0.34
    Activations Density 0.000%

    No Known Activations