© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    4. 235572
    Prev
    Next
    INDEX
    Explanations

    hoping to avoid war

    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_32_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
     ଆ
    0.40
    riors
    0.40
     राजू
    0.39
     विन
    0.38
    聘
    0.38
    ͈
    0.37
    警
    0.37
     農
    0.37
    }={
    0.36
     आइकन
    0.36
    POSITIVE LOGITS
    Wrong
    0.40
     Wrong
    0.39
     eyelash
    0.38
     indel
    0.37
     traitor
    0.37
    Mechanical
    0.35
     избе
    0.35
     Aber
    0.34
    ティーク
    0.34
     selalu
    0.34
    Activations Density 0.001%

    No Known Activations