© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 77370
    Prev
    Next
    INDEX
    Explanations

    abbreviations and citations

    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_53_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
    𝔹
    0.40
     Raúl
    0.39
    ர்ப்ப
    0.38
    igenes
    0.37
    न्दा
    0.37
    ಸು
    0.36
    landish
    0.35
    estine
    0.35
    𝐖
    0.34
    ณฑ์
    0.34
    POSITIVE LOGITS
     bit
    0.38
    ;;
    0.38
     breakthrough
    0.37
     et
    0.36
     &-
    0.35
     gang
    0.34
     ono
    0.34
     dica
    0.34
     Survey
    0.33
     crème
    0.33
    Activations Density 0.001%

    No Known Activations