© 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. 79745
    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
    為什麼
    0.42
     motivation
    0.42
     вклю
    0.42
     motivación
    0.41
     Motivation
    0.40
     时
    0.40
     작업
    0.40
    禪
    0.39
     motivations
    0.39
    为什么
    0.39
    POSITIVE LOGITS
     хотелось
    0.40
    Immediate
    0.39
    GID
    0.38
     Islands
    0.37
    GLE
    0.36
    uli
    0.35
     ||
    0.35
     HH
    0.35
     fallait
    0.35
     islands
    0.35
    Activations Density 0.000%

    No Known Activations