© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 13305
    Prev
    Next
    INDEX
    Explanations

    the word "child" or "children."

    oai_token-act-pair · gemini-2.0-flash

    child

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     child
    -2.47
     Child
    -2.14
    Child
    -2.13
    child
    -2.08
     CHILD
    -1.89
    CHILD
    -1.61
     childs
    -1.39
     Childs
    -1.12
     enfant
    -1.07
    childs
    -1.02
    POSITIVE LOGITS
     combineReducers
    0.56
    ütün
    0.54
    ofern
    0.52
     interceptor
    0.50
     AttributeSet
    0.50
     DBNull
    0.50
    JspWriter
    0.49
     */;
    0.48
    řád
    0.48
     radiators
    0.48
    Activations Density 0.415%

    No Known Activations