© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 84334
    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_0_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
    Sym
    0.57
    Single
    0.55
    ist
    0.55
    Waters
    0.54
    Dat
    0.53
    Mot
    0.53
    Virtual
    0.53
    I
    0.53
    Tre
    0.52
    Crane
    0.52
    POSITIVE LOGITS
     overtaken
    0.64
     inflamed
    0.64
     undermined
    0.61
     subsided
    0.59
     intersected
    0.59
     phosphorylated
    0.57
     conjectured
    0.57
     incubating
    0.56
     excised
    0.55
     assailant
    0.55
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.