© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 181844
    Prev
    Next
    INDEX
    Explanations

    person or entity descriptors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_29_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
    billing
    0.41
    阁
    0.39
     jealous
    0.37
     succeeds
    0.36
     oversees
    0.35
    initializing
    0.35
     initializing
    0.35
     النج
    0.35
     giỏi
    0.34
    sene
    0.34
    POSITIVE LOGITS
     vortex
    0.37
     spiral
    0.35
     randomly
    0.34
    હીં
    0.34
     mobilisation
    0.34
     random
    0.33
     "
    0.33
    Circular
    0.33
    Random
    0.32
     famosos
    0.32
    Activations Density 0.007%

    No Known Activations