© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 106248
    Prev
    Next
    INDEX
    Explanations

    Natural language inference

    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_44_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
    一郎
    0.41
    ILLE
    0.40
    ｪ
    0.38
     elliptical
    0.37
    <0xB6>
    0.36
    kum
    0.36
     Moch
    0.36
    Щ
    0.36
     표준
    0.35
    ěř
    0.35
    POSITIVE LOGITS
     weeding
    0.45
     zuten
    0.40
     inevitably
    0.38
     doctrines
    0.38
     conflicts
    0.38
     scaffold
    0.37
     サイド
    0.36
     weed
    0.36
    :`
    0.36
    padding
    0.36
    Activations Density 0.003%

    No Known Activations