© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 84262
    Prev
    Next
    INDEX
    Explanations

    gain and following words

    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_0_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
    س
    2.05
    t
    1.94
    ل
    1.72
    uk
    1.68
    ت
    1.68
    ی
    1.64
    ir
    1.38
    ut
    1.30
    tä
    1.28
    ebar
    1.27
    POSITIVE LOGITS
     và
    1.34
    示す
    1.27
     ແລະ
    1.26
    ous
    1.24
     של
    1.22
    것
    1.21
     וה
    1.19
    つ
    1.19
     እንዲሁም
    1.18
     ות
    1.17
    Activations Density 0.002%

    No Known Activations