© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 3915
    Prev
    Next
    INDEX
    Explanations

    EC2 Stop firewalld hardware IP

    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_39_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
    脱
    0.43
    脫
    0.42
     defens
    0.36
     Global
    0.36
     ग्लोबल
    0.36
     Stef
    0.35
    Lisa
    0.35
    ]::
    0.35
    Global
    0.35
     Microsoft
    0.34
    POSITIVE LOGITS
    鼻
    0.47
     ignition
    0.44
     nova
    0.43
     Ignition
    0.43
    nova
    0.41
     commandant
    0.41
     storms
    0.41
    রী
    0.40
     supernova
    0.40
     passwd
    0.39
    Activations Density 0.142%

    No Known Activations