© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 235923
    Prev
    Next
    INDEX
    Explanations

    cash

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
     flow
    1.42
     Flow
    1.34
    flow
    1.29
    Flow
    1.27
     FLOW
    1.18
    FLOW
    1.17
     flujo
    1.00
    流
    0.95
     flows
    0.93
     Flows
    0.86
    POSITIVE LOGITS
     कैश
    0.45
    的手
    0.40
    現金
    0.40
    eared
    0.38
     cash
    0.37
    oked
    0.37
     হাতে
    0.37
    दयाल
    0.37
    を手
    0.36
     Lec
    0.36
    Activations Density 0.001%

    No Known Activations