© 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. 43-GEMMASCOPE-2-TRANSCODER-262K
    7. 212597
    Prev
    Next
    INDEX
    Explanations

    numbers and waves

    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_43_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
    Plasma
    0.42
     plasma
    0.39
     Plasma
    0.39
     decoupled
    0.39
    Grav
    0.38
    bypass
    0.37
    ██
    0.37
    CREATED
    0.35
    August
    0.35
     Graft
    0.35
    POSITIVE LOGITS
     c
    0.53
     waves
    0.41
     tiểu
    0.39
     المنتخب
    0.38
    HRIM
    0.38
     Tudor
    0.38
     ঢেউ
    0.37
     numbers
    0.37
     समझते
    0.37
     apparten
    0.37
    Activations Density 0.025%

    No Known Activations