© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 4330
    Prev
    Next
    INDEX
    Explanations

    names ending with ian or ick

    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_40_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
    ड्रन
    0.40
     cmdlet
    0.38
    nod
    0.38
     informasjon
    0.37
    uffed
    0.37
    㶱
    0.37
     ఇన్
    0.36
    ቷ
    0.36
    omat
    0.36
     Boden
    0.36
    POSITIVE LOGITS
    minor
    0.41
    ján
    0.40
    âmb
    0.39
     pret
    0.38
    jan
    0.38
     occupancy
    0.38
    ianz
    0.38
    Santiago
    0.37
     phí
    0.37
    培養
    0.37
    Activations Density 0.008%

    No Known Activations