© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 59821
    Prev
    Next
    INDEX
    Explanations

    rather followed by descriptive adjectives

    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_11_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
    рила
    0.67
     Oko
    0.60
     Semi
    0.59
     Sự
    0.59
    مدينة
    0.59
    Những
    0.59
    هي
    0.59
    Н
    0.59
    他们
    0.58
     Một
    0.57
    POSITIVE LOGITS
     springboard
    0.66
    ми
    0.64
     ontology
    0.64
     scope
    0.61
     blockchain
    0.60
     candid
    0.59
     competency
    0.58
     qualifier
    0.57
     scaffold
    0.57
     library
    0.57
    Activations Density 0.004%

    No Known Activations