© 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. 58823
    Prev
    Next
    INDEX
    Explanations

    pirate speech: arr, me, ye, lads

    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
    마트
    0.65
    ტერ
    0.63
    j
    0.61
     réfrig
    0.60
    t
    0.60
    hält
    0.59
     nád
    0.59
    ună
    0.59
    стам
    0.58
     lymphatiques
    0.58
    POSITIVE LOGITS
    ating
    0.62
     o
    0.55
    ения
    0.55
    ım
    0.55
    icleta
    0.54
    ressing
    0.54
     d
    0.53
     s
    0.52
     ១
    0.52
     cynicism
    0.51
    Activations Density 0.018%

    No Known Activations