© 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. 200694
    Prev
    Next
    INDEX
    Explanations

    US

    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
    ame
    0.46
    idge
    0.41
    mid
    0.40
     ame
    0.40
    ፈር
    0.38
    ilane
    0.38
     frapp
    0.37
    <0xB2>
    0.36
    bid
    0.35
     kaip
    0.35
    POSITIVE LOGITS
     Issa
    0.41
    ঔ
    0.40
     لدي
    0.39
    遺
    0.39
     Leningrad
    0.38
    riots
    0.38
    舩
    0.38
    setRoot
    0.38
     généraux
    0.38
     Genomics
    0.37
    Activations Density 0.000%

    No Known Activations