© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 76577
    Prev
    Next
    INDEX
    Explanations

    demolish buildings

    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
     farewell
    0.46
     desped
    0.46
     goodbye
    0.45
     parted
    0.42
     Goodbye
    0.40
     hometown
    0.39
     Farewell
    0.39
    烘
    0.37
     ули
    0.37
     fireworks
    0.36
    POSITIVE LOGITS
     Dise
    0.40
    Manu
    0.39
    掺
    0.38
    琭
    0.38
    慢性
    0.37
    棟
    0.37
    NoError
    0.37
    檴
    0.36
    rochemical
    0.36
     choroby
    0.36
    Activations Density 0.003%

    No Known Activations