© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 236096
    Prev
    Next
    INDEX
    Explanations

    lookarounds and regex syntax

    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_32_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
    міністра
    0.48
     তেলেভ
    0.40
    ército
    0.39
    μένα
    0.38
     prohib
    0.38
    ەش
    0.37
    脅
    0.37
    溽
    0.37
     dil
    0.36
    clesi
    0.36
    POSITIVE LOGITS
    éns
    0.38
     управля
    0.37
    ppy
    0.36
     Controlled
    0.36
     Rxg
    0.35
    tokenize
    0.35
    unas
    0.34
     Schema
    0.34
    ető
    0.34
     asseg
    0.34
    Activations Density 0.001%

    No Known Activations