© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 246251
    Prev
    Next
    INDEX
    Explanations

    head and neck

    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_40_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
     Texture
    0.58
     textures
    0.54
     texture
    0.53
     тексту
    0.52
    Texture
    0.51
    texture
    0.50
     textura
    0.48
     c
    0.45
    TabText
    0.43
    TEXTURE
    0.41
    POSITIVE LOGITS
     ding
    0.41
     neck
    0.41
    heel
    0.41
    ಧಾನ
    0.39
     गर्दन
    0.39
    Neck
    0.38
    head
    0.37
    머
    0.37
    RET
    0.37
     necks
    0.37
    Activations Density 0.042%

    No Known Activations