© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 170876
    Prev
    Next
    INDEX
    Explanations

    a

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     crowd
    0.50
     monstrous
    0.44
     Crowd
    0.44
     mine
    0.39
     அணுக
    0.38
     awaited
    0.38
    众
    0.36
     wondrous
    0.35
     breeze
    0.35
     flashing
    0.35
    POSITIVE LOGITS
    Great
    0.47
     Great
    0.44
     лучшие
    0.42
     BEST
    0.42
     favorites
    0.41
     بهترین
    0.41
    Best
    0.39
     GREAT
    0.39
    BEST
    0.39
     W
    0.38
    Activations Density 0.013%

    No Known Activations