© 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. 167697
    Prev
    Next
    INDEX
    Explanations

    Romanov, dynasty, royal, Antoinette

    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
     익
    0.38
     Eros
    0.38
    充分
    0.38
    matik
    0.37
     Stuck
    0.36
    Sliders
    0.35
    testAvg
    0.35
    Speak
    0.34
     razones
    0.34
     Speak
    0.34
    POSITIVE LOGITS
    rais
    0.41
     tinted
    0.38
    legi
    0.38
    礁
    0.37
    apur
    0.37
     beni
    0.37
    ',['
    0.37
     மீட்ப
    0.36
    ◽
    0.36
    endance
    0.36
    Activations Density 0.000%

    No Known Activations