© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 175844
    Prev
    Next
    INDEX
    Explanations

    Ukrainian cities

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
     L
    0.71
    L
    0.60
     Л
    0.57
    𝐿
    0.55
     LC
    0.52
     LPC
    0.52
    𝑳
    0.51
    ば
    0.50
     Lx
    0.49
    Л
    0.49
    POSITIVE LOGITS
    Dag
    0.43
    dag
    0.38
     Dag
    0.38
     dag
    0.36
     prophecy
    0.36
     Peter
    0.35
    DAG
    0.35
    sel
    0.34
    ஸ்ப
    0.34
    vals
    0.34
    Activations Density 0.000%

    No Known Activations