© 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. 206161
    Prev
    Next
    INDEX
    Explanations

    clothing and body

    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
     网
    0.44
     meshes
    0.42
    網
    0.42
     сет
    0.41
    listeners
    0.40
    网
    0.40
    mesh
    0.40
    PSD
    0.40
    宫
    0.39
     lor
    0.39
    POSITIVE LOGITS
    ∀
    0.41
     ∀
    0.41
     Văn
    0.40
     văn
    0.39
    forall
    0.39
    くなり
    0.38
     Snackbar
    0.38
    িশীল
    0.37
     toothpaste
    0.37
     Textbook
    0.37
    Activations Density 0.038%

    No Known Activations