© 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. 18596
    Prev
    Next
    INDEX
    Explanations

    java HashMap ArrayList Alfred Hitchcock

    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
     distillation
    0.43
     expel
    0.36
     visitor
    0.36
    antlr
    0.35
    validated
    0.35
     Ped
    0.35
     角
    0.34
     APC
    0.34
    角
    0.34
     visitors
    0.34
    POSITIVE LOGITS
    蘇
    0.41
     लंदन
    0.41
    ল্যান্ড
    0.39
     লন্ডন
    0.39
    abhavam
    0.39
     Lond
    0.38
     london
    0.38
    london
    0.37
     plán
    0.37
    honia
    0.37
    Activations Density 0.012%

    No Known Activations