© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12920
    Prev
    Next
    INDEX
    Explanations

    words related to substance use disorder, treatment, and associated behaviors.

    oai_token-act-pair · gemini-2.0-flash

    Substance and alcohol abuse

    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
     estekak
    -0.66
    IonicModule
    -0.60
     transferência
    -0.57
     ffilm
    -0.54
    şört
    -0.53
    ResponseWriter
    -0.52
    URLException
    -0.52
    oredCriteria
    -0.50
    出版年
    -0.50
    clés
    -0.50
    POSITIVE LOGITS
    Portale
    0.57
    Portail
    0.50
     StringTokenizer
    0.50
    evos
    0.49
    ipts
    0.49
     stimulants
    0.48
    resenta
    0.47
    istoitu
    0.47
    ruik
    0.45
    ATUS
    0.45
    Activations Density 4.214%

    No Known Activations