© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 88529
    Prev
    Next
    INDEX
    Explanations

    ongoing actions or states

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_60_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
     foram
    0.53
     fick
    0.52
    し
    0.51
     are
    0.50
     furono
    0.49
     fueron
    0.45
     blev
    0.44
     is
    0.44
    しました
    0.44
    了
    0.44
    POSITIVE LOGITS
    have
    0.59
     Have
    0.58
    Have
    0.58
     have
    0.56
    えている
    0.55
    ıyor
    0.53
    となっている
    0.52
     έχει
    0.52
     έχουν
    0.52
    有一个
    0.51
    Activations Density 0.000%

    No Known Activations