© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 64436
    Prev
    Next
    INDEX
    Explanations

    stretching

    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_46_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
     robbing
    0.50
     fire
    0.46
     Fire
    0.45
     robber
    0.45
     commanding
    0.45
     clover
    0.45
     nail
    0.44
    火
    0.44
     Commanding
    0.44
     Nail
    0.43
    POSITIVE LOGITS
     stretch
    0.43
    stretch
    0.41
    Kan
    0.37
    ুত
    0.37
    PIN
    0.36
    ശ്
    0.35
    AKE
    0.35
     Stretch
    0.35
     stretches
    0.34
     زوج
    0.34
    Activations Density 0.006%

    No Known Activations