© 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-2-2B
    5. 23-GEMMASCOPE-TRANSCODER-16K
    7. 13281
    Prev
    Next
    INDEX
    Explanations

    phrases indicating negativity or something undesirable

    oai_token-act-pair · gemini-2.0-flash

    in

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CreateTagHelper
    -0.77
     nahilalakip
    -0.66
    webElementXpaths
    -0.64
    featureID
    -0.63
     jScrollPane
    -0.60
    KURZBESCHREIBUNG
    -0.58
     חיצוניים
    -0.57
    DockStyle
    -0.55
     Baillargeon
    -0.54
    asaan
    -0.54
    POSITIVE LOGITS
     in
    1.15
     In
    0.68
     în
    0.60
    InThe
    0.59
     inline
    0.57
    In
    0.56
     в
    0.55
    inthe
    0.54
    indata
    0.52
    ใน
    0.50
    Activations Density 4.169%

    No Known Activations