© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 122043
    Prev
    Next
    INDEX
    Explanations

    charge, effect, impacts

    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_3_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
    x
    0.84
    i
    0.83
    ent
    0.81
    an
    0.73
    hmm
    0.65
    a
    0.64
    all
    0.63
    microseconds
    0.63
    berries
    0.63
    that
    0.62
    POSITIVE LOGITS
     to
    1.02
     are
    0.95
    یت
    0.83
    する
    0.72
    =\
    0.70
    ോ
    0.70
    ін
    0.69
    िस
    0.68
     meningkatkan
    0.68
     trás
    0.67
    Activations Density 0.001%

    No Known Activations