© 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. 215207
    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
     hoax
    0.40
    Ū
    0.40
    ->"
    0.39
    +}^{
    0.39
     іх
    0.38
     then
    0.38
     annealing
    0.38
    磷
    0.38
     tormented
    0.37
     Jol
    0.37
    POSITIVE LOGITS
    upgrade
    0.39
    texts
    0.37
     сп
    0.37
    hp
    0.36
    MSP
    0.34
    LG
    0.34
    oga
    0.33
    cnt
    0.33
    市場
    0.33
     χω
    0.33
    Activations Density 0.000%

    No Known Activations