© 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. 31835
    Prev
    Next
    INDEX
    Explanations

    Donald

    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
     बीटल
    0.46
    Tr
    0.42
     trist
    0.41
    orbit
    0.40
     سفید
    0.39
    鄴
    0.39
     Tris
    0.38
     orbits
    0.38
     trach
    0.38
    вим
    0.37
    POSITIVE LOGITS
    CNR
    0.44
    昦
    0.39
     Reno
    0.38
    Brent
    0.38
     Brentwood
    0.37
     Renato
    0.37
    லி
    0.37
    平台的
    0.37
    QN
    0.36
    zj
    0.36
    Activations Density 0.001%

    No Known Activations