© 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. 10364
    Prev
    Next
    INDEX
    Explanations

    nim programming language

    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
     Motley
    0.40
    帮你
    0.39
     TEAM
    0.37
    聋
    0.36
     totalement
    0.36
    ्युनिकेशन
    0.36
     메서
    0.36
    Steven
    0.36
    ٨
    0.36
    顛
    0.36
    POSITIVE LOGITS
     NIM
    0.41
     provocation
    0.38
     Invit
    0.38
    ImmediateContext
    0.37
     Nim
    0.37
    GRP
    0.34
    blest
    0.34
    data
    0.34
     nim
    0.34
     provoc
    0.34
    Activations Density 0.011%

    No Known Activations