© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 198607
    Prev
    Next
    INDEX
    Explanations

    "Hed"

    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_50_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
    雍
    0.38
    ች
    0.38
     behandling
    0.37
     తు
    0.37
    feng
    0.36
     Função
    0.36
    锋
    0.36
     lib
    0.35
     DMC
    0.35
     Liberation
    0.33
    POSITIVE LOGITS
    Hed
    0.46
     hed
    0.45
     Hed
    0.44
    hed
    0.44
     品
    0.43
     Great
    0.42
    hede
    0.42
    Great
    0.41
     Porte
    0.40
    heds
    0.40
    Activations Density 0.000%

    No Known Activations