© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 110232
    Prev
    Next
    INDEX
    Explanations

    words ending in common suffixes such as 'er' and 'ing'

    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_2_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
    a
    1.58
    ਰ
    1.23
    \
    1.22
    in
    1.19
    ه
    1.09
    aing
    1.07
    IT
    1.05
    ال
    1.00
     I
    0.99
    ’
    0.99
    POSITIVE LOGITS
    ле
    1.38
    ти
    1.23
    ק
    1.23
    си
    1.23
    та
    1.18
    ،
    1.17
    но
    1.12
    ీ
    1.05
    ls
    1.02
    ة
    1.02
    Activations Density 0.001%

    No Known Activations