© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 100461
    Prev
    Next
    INDEX
    Explanations

    natural persons

    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_14_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
     簡単
    0.17
     comenzamos
    0.15
     Quadrupèdes
    0.15
     如何
    0.15
     Обычно
    0.15
     규칙
    0.15
     எவ்வாறு
    0.15
    🠀
    0.14
     échantillons
    0.14
    ാന്‍
    0.14
    POSITIVE LOGITS
    James
    0.14
    "
    0.13
    P
    0.13
    GET
    0.12
     "
    0.12
    David
    0.12
    Profes
    0.12
    Scient
    0.12
     James
    0.11
     \
    0.11
    Activations Density 0.003%

    No Known Activations