© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 75495
    Prev
    Next
    INDEX
    Explanations

    how followed by adjective/adverb

    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
     ничек
    0.37
     UInt
    0.35
     ün
    0.35
     cland
    0.35
     Mö
    0.34
     Barrett
    0.34
     случаи
    0.34
    џ
    0.33
     Reglamento
    0.33
     دون
    0.33
    POSITIVE LOGITS
     chav
    0.36
    washed
    0.35
    ale
    0.34
    ombies
    0.34
    amber
    0.34
    ጨ
    0.34
    ravy
    0.34
    ymmetries
    0.34
    ∆
    0.33
     difficile
    0.33
    Activations Density 0.004%

    No Known Activations