© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 164914
    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
    それは
    0.45
     daar
    0.44
     우리는
    0.41
     হিন্দুদের
    0.40
    нт
    0.39
    ид
    0.39
     {},
    0.38
     그는
    0.38
    ние
    0.38
    あなたは
    0.38
    POSITIVE LOGITS
     deserve
    0.40
     want
    0.39
     piya
    0.38
     quiso
    0.36
     mérite
    0.36
     owe
    0.36
     lysosomes
    0.34
    foration
    0.34
     evokes
    0.33
     کرتا
    0.33
    Activations Density 0.000%

    No Known Activations