© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 138233
    Prev
    Next
    INDEX
    Explanations

    concepts related to abstract nouns

    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_37_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
    Cruz
    0.41
     hearts
    0.38
    \}
    0.37
    াড়াও
    0.37
     Herzen
    0.36
     tombs
    0.35
    IndexArray
    0.35
     lòng
    0.35
     vět
    0.34
     lets
    0.34
    POSITIVE LOGITS
    ของผู้
    0.46
    របស់
    0.43
     людини
    0.43
     врача
    0.39
    plate
    0.38
    anyone
    0.37
     автора
    0.37
     봄
    0.37
     человека
    0.36
     пациента
    0.36
    Activations Density 0.125%

    No Known Activations