© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 152973
    Prev
    Next
    INDEX
    Explanations

    **rries**

    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_23_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
    ➝
    0.39
    威胁
    0.38
    Դ
    0.37
    否则
    0.37
     YES
    0.36
    Здравствуйте
    0.36
    ਟੀ
    0.36
     pinpoint
    0.35
     tweak
    0.35
    🎳
    0.35
    POSITIVE LOGITS
    rican
    0.49
    ismo
    0.47
    irse
    0.42
    ador
    0.41
    ismus
    0.41
    ቻል
    0.41
     Future
    0.40
    ric
    0.39
    ricanes
    0.39
    ator
    0.39
    Activations Density 0.001%

    No Known Activations