© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 27995
    Prev
    Next
    INDEX
    Explanations

    224x224 image size

    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_40_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
    Blake
    0.42
    anteen
    0.39
    orescent
    0.37
     laughable
    0.37
    Complaint
    0.37
    ༧
    0.37
     প্রত্যক্ষ
    0.36
     Blake
    0.36
    翳
    0.36
     hInstance
    0.36
    POSITIVE LOGITS
     hacking
    0.40
     netted
    0.38
     length
    0.38
     tet
    0.37
     lenght
    0.36
    yld
    0.36
     призна
    0.36
     Getting
    0.36
     rhe
    0.36
     Hack
    0.36
    Activations Density 0.002%

    No Known Activations