© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 21632
    Prev
    Next
    INDEX
    Explanations

    naming or calling

    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_56_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
    izare
    0.34
    짐
    0.34
    ulai
    0.33
     வீர
    0.33
    ayak
    0.33
    Vij
    0.32
    RecordPtr
    0.32
    部署
    0.32
     Blatt
    0.32
    ㄻ
    0.31
    POSITIVE LOGITS
     named
    2.52
    named
    2.31
    Named
    2.30
     Named
    2.23
     nommé
    1.75
     bernama
    1.70
     labelled
    1.63
     labeled
    1.63
     titled
    1.61
     called
    1.53
    Activations Density 0.401%

    No Known Activations