© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 148940
    Prev
    Next
    INDEX
    Explanations

    divisible by 3 or 5

    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_18_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
     grieving
    0.57
     grief
    0.44
     tasteless
    0.43
     bereaved
    0.42
     birth
    0.42
     rekind
    0.41
     unpacking
    0.41
    k
    0.41
     discouraging
    0.40
     Grief
    0.40
    POSITIVE LOGITS
    基于
    0.48
     基于
    0.44
    世纪
    0.44
     Liechtenstein
    0.43
     totalidad
    0.43
     特定
    0.42
    imageNamed
    0.42
    ланган
    0.42
    ایہ
    0.42
     Zentrum
    0.41
    Activations Density 0.003%

    No Known Activations