© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 102513
    Prev
    Next
    INDEX
    Explanations

    amplification or amplification related

    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_14_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
    BLY
    0.48
     photons
    0.48
    JA
    0.46
    )/(
    0.45
    lni
    0.45
     believable
    0.45
    ('$(
    0.45
    Neurons
    0.44
     Cualquier
    0.44
    ).</
    0.44
    POSITIVE LOGITS
     يق
    0.62
    峡
    0.56
     منتشر
    0.56
     regurg
    0.55
     gastro
    0.55
     deve
    0.54
     Bible
    0.54
     Lal
    0.53
     یق
    0.53
     Mons
    0.51
    Activations Density 0.016%

    No Known Activations