© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 101984
    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_14_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
     ચ
    0.57
     pasan
    0.57
     cheetah
    0.57
     кисло
    0.54
    ört
    0.53
     cận
    0.52
    vvvert
    0.52
     eryth
    0.52
    ᱙
    0.52
    obe
    0.51
    POSITIVE LOGITS
    values
    0.53
    I
    0.51
    ctuation
    0.48
     edges
    0.46
    ടതി
    0.46
    ዻ
    0.46
    єдна
    0.45
    \
    0.45
    elements
    0.44
     Values
    0.44
    Activations Density 0.000%

    No Known Activations