© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 226494
    Prev
    Next
    INDEX
    Explanations

    blood flow

    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_10_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
    е
    1.02
    ן
    0.91
    ur
    0.89
    ni
    0.88
    ی
    0.88
    ut
    0.87
    illed
    0.86
    ry
    0.86
    ili
    0.85
    і
    0.84
    POSITIVE LOGITS
     flow
    1.44
    Flow
    1.35
     Flow
    1.24
    a
    1.17
    FLOW
    1.11
     flows
    1.07
     FLOW
    1.04
    flow
    1.00
    u
    0.91
    ج
    0.91
    Activations Density 0.011%

    No Known Activations