© 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. 200911
    Prev
    Next
    INDEX
    Explanations

    code and data

    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
     তথা
    0.43
    څ
    0.39
    ኵ
    0.35
    ació
    0.35
     lửa
    0.35
    acions
    0.34
     bzw
    0.34
    Dé
    0.34
    ຕ
    0.33
    hö
    0.33
    POSITIVE LOGITS
     ಮಾಡುವ
    0.36
     stu
    0.33
     articulation
    0.32
     باذن
    0.32
    рованным
    0.32
    Veg
    0.32
     illuminate
    0.31
     imperative
    0.31
     اوقات
    0.31
     germinate
    0.31
    Activations Density 0.145%

    No Known Activations