© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 37212
    Prev
    Next
    INDEX
    Explanations

    transaction, merchant, balance, value

    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_11_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
    Ke
    0.52
    伒
    0.46
    Ha
    0.45
    Har
    0.44
    FQ
    0.44
    pcid
    0.43
    Kü
    0.43
    㓶
    0.43
    že
    0.42
    Implementation
    0.42
    POSITIVE LOGITS
     его
    0.47
     controls
    0.42
    発電
    0.42
    根
    0.39
    controls
    0.38
     BUSINESS
    0.38
     это
    0.38
    ویی
    0.38
     frug
    0.38
     tuition
    0.38
    Activations Density 0.052%

    No Known Activations