© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 136703
    Prev
    Next
    INDEX
    Explanations

    recogn, exerc, anticip, employ

    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_12_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
    ury
    0.60
    ت
    0.55
    ъ
    0.55
    ah
    0.54
     Konzept
    0.54
     HPC
    0.54
    া
    0.54
    intuitive
    0.54
    బంధ
    0.53
    overe
    0.53
    POSITIVE LOGITS
     то
    0.64
     to
    0.59
    InfoPlistPath
    0.57
     ನೀರಿನ
    0.56
     볼
    0.55
     tubig
    0.55
    DanhMucSP
    0.54
     electrónica
    0.53
     marcado
    0.52
     резко
    0.52
    Activations Density 0.010%

    No Known Activations