© 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. 63336
    Prev
    Next
    INDEX
    Explanations

    names/technical terms

    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
    星星
    0.44
     prerequisites
    0.40
    ilu
    0.39
    晟
    0.39
    Culture
    0.38
    pd
    0.38
     screenings
    0.37
     Гали
    0.37
    ifiers
    0.37
    ifications
    0.37
    POSITIVE LOGITS
    quo
    0.38
    ︡
    0.36
    ACA
    0.36
     शख
    0.35
     thematic
    0.35
     الاد
    0.35
     জামাল
    0.34
    zial
    0.34
     incompl
    0.34
     Alonzo
    0.34
    Activations Density 0.008%

    No Known Activations