© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 2634
    Prev
    Next
    INDEX
    Explanations

    9

    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_44_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
     Cause
    0.38
    撻
    0.37
     Bedford
    0.37
    olica
    0.37
     Ria
    0.37
     Incidence
    0.36
     instar
    0.36
    licas
    0.34
     CYCLE
    0.34
     incidence
    0.34
    POSITIVE LOGITS
    Performing
    0.39
    ⃣
    0.39
    '*
    0.37
    팔
    0.37
    ni
    0.36
     wale
    0.36
    아
    0.36
    ers
    0.36
    rive
    0.36
     anymore
    0.36
    Activations Density 0.112%

    No Known Activations