© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 52366
    Prev
    Next
    INDEX
    Explanations

    certain words and suffixes

    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_31_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
    वेदना
    0.35
    첼
    0.35
    कत
    0.34
    蜚
    0.34
    кат
    0.33
    εις
    0.33
    בור
    0.32
     אל
    0.32
    균
    0.32
    CONCLUSION
    0.32
    POSITIVE LOGITS
     mainly
    0.38
     principalement
    0.35
     staged
    0.34
     කරයි
    0.34
     दर्शाता
    0.33
     principalmente
    0.33
     encanta
    0.33
     geht
    0.32
    stdint
    0.31
    說是
    0.31
    Activations Density 0.002%

    No Known Activations