© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 4028
    Prev
    Next
    INDEX
    Explanations

    -aster, -ester, -ister, -ster endings

    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_40_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
    line
    0.43
    bic
    0.41
    concent
    0.39
    fassung
    0.39
     ఊ
    0.39
    layan
    0.38
    Line
    0.38
     erw
    0.38
     concent
    0.37
    wave
    0.37
    POSITIVE LOGITS
    Could
    0.41
     Could
    0.41
    :'.
    0.41
    方位
    0.39
     породы
    0.39
     alamat
    0.38
    ब्बत
    0.38
    委员
    0.37
     COULD
    0.37
     could
    0.36
    Activations Density 0.000%

    No Known Activations