© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10519
    Prev
    Next
    INDEX
    Explanations

    java code related to setting and getting parameters

    oai_token-act-pair · gemini-2.0-flash

    set

    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
    Nro
    -0.66
    Error
    -0.59
    Subject
    -0.57
    FirstName
    -0.55
    Attribute
    -0.55
     للمعارف
    -0.54
    rboles
    -0.52
    Output
    -0.52
    Enabled
    -0.52
    DockStyle
    -0.52
    POSITIVE LOGITS
     defaultstate
    0.57
    ConstraintMaker
    0.57
     WebApplication
    0.55
    joba
    0.54
    CrossRef
    0.53
    removeChild
    0.52
    richTextPanel
    0.50
    reactstrap
    0.48
     ISNI
    0.48
    ggiata
    0.48
    Activations Density 0.849%

    No Known Activations