© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 167625
    Prev
    Next
    INDEX
    Explanations

    world vs external pressures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_34_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
    anjang
    0.40
     Bergen
    0.38
    Universe
    0.38
    NJ
    0.38
    beros
    0.38
    ಟ್ಟಿ
    0.38
    urches
    0.37
    }{|
    0.37
     ধর্মের
    0.36
     MAKEINTRESOURCE
    0.36
    POSITIVE LOGITS
    ዜ
    0.40
    潮
    0.39
     radeon
    0.36
     جنرل
    0.35
     ahuv
    0.35
     Amitabh
    0.35
    AddItem
    0.35
    毂
    0.35
    傈
    0.34
     fruit
    0.34
    Activations Density 0.002%

    No Known Activations