© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 4652
    Prev
    Next
    INDEX
    Explanations

    objective-c code, particularly keywords like self, alloc, pointer, add, action, and selector

    oai_token-act-pair · gemini-2.0-flash

    self alloc

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    NameInMap
    -0.68
     kasarigan
    -0.66
     įsi
    -0.65
    CodeAttribute
    -0.65
    sidemargin
    -0.64
    __*/
    -0.62
    XmlAccessType
    -0.60
    ंदीखरीदारी
    -0.60
     دیکھیے
    -0.60
     ['./
    -0.59
    POSITIVE LOGITS
    CGRectMake
    0.63
    nonatomic
    0.62
     NSObject
    0.60
     nonatomic
    0.60
    IBarButtonItem
    0.58
     handleMessage
    0.58
    forKey
    0.54
    CGRect
    0.54
    UILabel
    0.52
    UIControlState
    0.52
    Activations Density 0.031%

    No Known Activations