© 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. 165984
    Prev
    Next
    INDEX
    Explanations

    technical and "-ing" words

    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
     Council
    0.41
     shepherd
    0.37
     duż
    0.36
    othèque
    0.35
    ັດ
    0.34
     काउंसिल
    0.34
    large
    0.34
    _{
    0.34
     donna
    0.34
     matemático
    0.34
    POSITIVE LOGITS
     metallurgy
    0.44
     развитие
    0.40
     развития
    0.40
    農業
    0.38
    Sampling
    0.38
     baseX
    0.38
    KQ
    0.38
     ವಿರು
    0.37
     здравоохра
    0.36
     инфраструк
    0.36
    Activations Density 0.042%

    No Known Activations