© 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-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 15709
    Prev
    Next
    INDEX
    Explanations

    content discussing the raising and disciplining of children and relations with parents.

    oai_token-act-pair · gemini-2.0-flash

    yelling

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    AndEndTag
    -0.78
     zuges
    -0.57
    Alike
    -0.55
    enumi
    -0.51
     provisoire
    -0.48
    ophores
    -0.47
     diterima
    -0.47
     caduta
    -0.47
     Nacionales
    -0.46
     étrangère
    -0.46
    POSITIVE LOGITS
     yelled
    0.65
     yell
    0.65
     yelling
    0.61
     <>",
    0.61
     grounded
    0.61
     grounding
    0.60
    Grounded
    0.59
    ForRow
    0.58
     yells
    0.57
    WithIOException
    0.57
    Activations Density 2.403%

    No Known Activations