© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 44-GEMMASCOPE-2-TRANSCODER-262K
    4. 104837
    Prev
    Next
    INDEX
    Explanations

    single-celled organism

    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
     मल्टीप्लिकेशन
    0.43
    bees
    0.41
    醀
    0.41
     பிரார்த்த
    0.40
    iritto
    0.38
    CIRC
    0.38
    olids
    0.38
     Донец
    0.38
     quadrature
    0.38
    olini
    0.38
    POSITIVE LOGITS
     extrem
    0.40
     mil
    0.37
    色
    0.36
    几个
    0.36
    estris
    0.36
     Piers
    0.36
     ജെ
    0.36
     Extreme
    0.35
     औ
    0.34
     starts
    0.34
    Activations Density 0.004%

    No Known Activations