© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 18530
    Prev
    Next
    INDEX
    Explanations

    Croatia and Croatian

    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_34_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
     Russland
    0.40
     Empowerment
    0.38
    腮
    0.37
     ಬದಲ
    0.37
     అభివృద్ధి
    0.37
     Yama
    0.37
    υκ
    0.37
     ইয়াহিয়া
    0.36
    Expo
    0.36
    ͒
    0.36
    POSITIVE LOGITS
     rtn
    0.42
    northern
    0.38
     alternatif
    0.37
     inadvertently
    0.37
     northern
    0.37
     alternate
    0.37
    setMin
    0.37
     coast
    0.37
     application
    0.36
     thru
    0.36
    Activations Density 0.002%

    No Known Activations