© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 246126
    Prev
    Next
    INDEX
    Explanations

    locomotives and trains

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_11_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
     killings
    0.56
    觜
    0.56
    offsetTop
    0.55
     repulsive
    0.55
     orchards
    0.54
     murderous
    0.53
     hilltop
    0.52
     killers
    0.52
     clinics
    0.52
     killing
    0.51
    POSITIVE LOGITS
    uega
    0.50
    졔
    0.48
    Elemental
    0.46
    Прави
    0.46
    玖
    0.45
    органи
    0.44
     사용
    0.44
    Japan
    0.44
    Format
    0.44
     Америка
    0.43
    Activations Density 0.000%

    No Known Activations