© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 896
    Prev
    Next
    INDEX
    Explanations

    you can afford to lose

    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
    ⌋
    0.38
    osław
    0.37
    ¿
    0.36
    ]+"
    0.36
     Stake
    0.36
    かを
    0.35
     जेट
    0.35
    聝
    0.35
     ¿
    0.34
    接着
    0.34
    POSITIVE LOGITS
     module
    0.46
    module
    0.42
     lac
    0.41
     modules
    0.40
    LAC
    0.40
    Module
    0.39
    MODULE
    0.38
     моду
    0.38
    extr
    0.37
     prescriptive
    0.37
    Activations Density 0.001%

    No Known Activations