© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 35343
    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_31_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
     jurid
    0.37
    組織
    0.36
     বিজয়
    0.36
    的重要性
    0.35
    Bechyné
    0.35
    ங்கா
    0.35
    级的
    0.34
    矫
    0.34
     فائد
    0.34
    임을
    0.34
    POSITIVE LOGITS
     Hex
    0.38
    box
    0.38
     leans
    0.37
     hexagon
    0.37
     knocks
    0.37
    瑤
    0.36
    ernos
    0.36
    awake
    0.36
    div
    0.35
     TextBox
    0.35
    Activations Density 0.000%

    No Known Activations