© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 53552
    Prev
    Next
    INDEX
    Explanations

    abstract algebra topology

    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_55_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
     semelhantes
    0.38
    снаб
    0.38
     veri
    0.37
    links
    0.37
     grouping
    0.36
     |=
    0.36
    IGroup
    0.35
    ēj
    0.35
     وجه
    0.35
     spricht
    0.35
    POSITIVE LOGITS
    новниш
    0.45
    洵
    0.38
    Rep
    0.38
     peacetime
    0.38
     inequ
    0.37
     populations
    0.37
    τευ
    0.37
    Sin
    0.37
    的问题
    0.37
    ấ
    0.37
    Activations Density 0.000%

    No Known Activations