© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 134874
    Prev
    Next
    INDEX
    Explanations

    nightstand and handstand

    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_1_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
    t
    2.22
    c
    1.61
    de
    1.59
    n
    1.47
    p
    1.39
    l
    1.38
    j
    1.34
    d
    1.28
    ين
    1.27
    m
    1.26
    POSITIVE LOGITS
    .}}
    1.08
     основ
    1.03
     ваши
    1.02
     efectivos
    1.01
     что
    1.00
    ри
    0.98
     форме
    0.98
     carbohyd
    0.98
     которому
    0.98
    ینا
    0.97
    Activations Density 0.001%

    No Known Activations