© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 33981
    Prev
    Next
    INDEX
    Explanations

    plural suffixes and past tense 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_3_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
     by
    1.73
     for
    1.43
    ر
    1.29
    ר
    1.29
    er
    1.16
     at
    1.13
    ER
    1.07
     and
    1.05
    ↵↵
    1.02
     into
    1.01
    POSITIVE LOGITS
    ی
    0.87
    ς
    0.86
     wasnt
    0.82
    ؑ
    0.79
     youll
    0.79
     informacje
    0.79
    সাথে
    0.77
    ySpeed
    0.77
     sexuales
    0.76
    impanan
    0.74
    Activations Density 0.001%

    No Known Activations