© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 258482
    Prev
    Next
    INDEX
    Explanations

    downloading content

    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_22_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
    “
    0.38
    ó
    0.38
     );
    0.38
     Entom
    0.38
    ()).
    0.38
    設立
    0.38
    的气
    0.37
    ').
    0.37
    ﺌ
    0.37
     suit
    0.37
    POSITIVE LOGITS
     জনগোষ্ঠীর
    0.43
    noodles
    0.41
    묭
    0.40
     まず
    0.40
     여기
    0.40
    ]]]]
    0.39
     রোগীদের
    0.39
     জনগণের
    0.39
     कैंपस
    0.38
    我们在
    0.38
    Activations Density 0.001%

    No Known Activations