© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 218172
    Prev
    Next
    INDEX
    Explanations

    planet or city names after punctuation

    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_31_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
    عليه
    0.40
     ئە
    0.39
    ە
    0.37
    על
    0.35
     كتب
    0.35
    因素
    0.33
    ラーメン
    0.33
     мнению
    0.33
    𒁍
    0.33
    irected
    0.33
    POSITIVE LOGITS
     exchangers
    0.43
    aks
    0.37
     каттоо
    0.37
     FIB
    0.36
    Hik
    0.35
     Dat
    0.35
     athlete
    0.35
     grids
    0.35
    hik
    0.35
     packs
    0.35
    Activations Density 0.001%

    No Known Activations