© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 202392
    Prev
    Next
    INDEX
    Explanations

    emergencias

    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_6_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
    h
    0.66
    f
    0.62
    thed
    0.61
    the
    0.59
    de
    0.57
    xz
    0.55
    al
    0.55
    dz
    0.53
    da
    0.53
    faktor
    0.52
    POSITIVE LOGITS
    ции
    0.66
    \
    0.66
    ется
    0.58
    ви
    0.53
     conseils
    0.53
     hoà
    0.53
     be
    0.51
     hòa
    0.51
    ъ
    0.51
     to
    0.50
    Activations Density 0.000%

    No Known Activations