© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 130583
    Prev
    Next
    INDEX
    Explanations

    digital

    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
     salve
    0.37
    ər
    0.36
    ::{
    0.36
     আরবি
    0.36
     clap
    0.35
     aus
    0.35
    iglich
    0.34
    IENTS
    0.34
     পর্যায়ে
    0.34
    Injury
    0.33
    POSITIVE LOGITS
    -.
    0.41
    εδ
    0.38
    মেঘ
    0.36
     tega
    0.36
    rektor
    0.36
     veranda
    0.34
     commutator
    0.34
    antam
    0.33
     "-"
    0.33
    ђа
    0.33
    Activations Density 0.005%

    No Known Activations