© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 131151
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Prince
    0.40
    MaxSize
    0.40
    businessman
    0.39
     Reihe
    0.38
    えない
    0.38
    íf
    0.37
    (*)
    0.37
    同
    0.37
     disappeared
    0.36
    Times
    0.36
    POSITIVE LOGITS
     alcanzar
    0.46
     đạt
    0.41
     ganas
    0.40
     AcOH
    0.40
    逹
    0.39
    OAc
    0.39
    緝
    0.39
     বক্তব্যে
    0.38
    inFile
    0.38
    AcOH
    0.38
    Activations Density 0.000%

    No Known Activations