© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 232353
    Prev
    Next
    INDEX
    Explanations

    inserting or subtracting numbers/substrings

    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_32_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
     overtake
    0.36
     supers
    0.36
     состояние
    0.34
    ịt
    0.34
    ווע
    0.34
     الول
    0.34
     resort
    0.33
    饑
    0.33
    洸
    0.33
     மீட்டர்
    0.33
    POSITIVE LOGITS
    inserts
    0.49
     inserts
    0.45
     inserted
    0.45
    INSERT
    0.44
    插入
    0.44
     inserting
    0.43
     insert
    0.43
    insert
    0.43
     smaller
    0.42
    少量
    0.42
    Activations Density 0.002%

    No Known Activations