© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 12262
    Prev
    Next
    INDEX
    Explanations

    court case descriptions involving children and alleged abuse and neglect

    oai_token-act-pair · gemini-2.0-flash

    juvenile/child

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    клопе
    -0.66
     enjo
    -0.54
     Rup
    -0.54
    ंदीखरीदारी
    -0.54
     autorytatywna
    -0.52
    irsi
    -0.52
    strophic
    -0.50
    loge
    -0.50
    енча
    -0.50
    protoc
    -0.49
    POSITIVE LOGITS
    LookAnd
    0.73
    WriteTagHelper
    0.73
    basicConfig
    0.60
     saurait
    0.58
    skosten
    0.52
     betweenstory
    0.49
    ControllerAdvice
    0.49
    LLocation
    0.49
    arques
    0.49
     BorderSide
    0.48
    Activations Density 3.885%

    No Known Activations