© 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
    2. Gemma-3-27B-IT
    3. 44-GEMMASCOPE-2-TRANSCODER-262K
    4. 105138
    Prev
    Next
    INDEX
    Explanations

    Minecraft building blocks

    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_44_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
     fog
    0.40
     infus
    0.39
    퓸
    0.39
     NFS
    0.38
     বিশ্রাম
    0.38
     نريد
    0.38
    钕
    0.38
     terminate
    0.37
     النبي
    0.36
     নীর
    0.36
    POSITIVE LOGITS
     Rik
    0.41
    គ្រប់
    0.40
     Buk
    0.39
    idev
    0.38
    Buk
    0.38
     Buj
    0.37
    journey
    0.36
    Proyecto
    0.36
    ㅂ
    0.35
    author
    0.35
    Activations Density 0.002%

    No Known Activations