© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 89732
    Prev
    Next
    INDEX
    Explanations

    idea generation

    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_11_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
     Entonces
    0.54
    ദ
    0.54
    东北
    0.52
    сім
    0.51
     Locale
    0.50
    共同
    0.49
     Relationship
    0.49
     Technologie
    0.49
    峒
    0.49
     Itália
    0.48
    POSITIVE LOGITS
     갖
    0.55
    anner
    0.54
     caseload
    0.52
     сро
    0.52
    al
    0.51
     gripper
    0.51
     غیر
    0.51
    annt
    0.49
     bygg
    0.49
     jukebox
    0.49
    Activations Density 0.000%

    No Known Activations