© 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. 131117
    Prev
    Next
    INDEX
    Explanations

    .

    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
    혈
    0.38
     ted
    0.36
    กิจ
    0.35
    ขั้น
    0.35
     Typed
    0.35
     Kits
    0.35
    騨
    0.35
    ศี
    0.34
     valor
    0.34
    시기
    0.34
    POSITIVE LOGITS
    amey
    0.44
    납
    0.40
    annam
    0.40
    jet
    0.40
    resu
    0.39
     insan
    0.39
    pbx
    0.39
    operateur
    0.39
    avi
    0.38
    طر
    0.38
    Activations Density 0.000%

    No Known Activations