© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 12258
    Prev
    Next
    INDEX
    Explanations

    code snippets, particularly from iOS (Objective-C) and Swift

    oai_token-act-pair · gemini-2.0-flash

    iOS UIKit code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     ROMAN
    -0.46
     Bohemia
    -0.45
     Marconi
    -0.42
     ),
    -0.41
     )$
    -0.41
    pl
    -0.41
     Lombard
    -0.41
     romana
    -0.39
     els
    -0.39
     portland
    -0.39
    POSITIVE LOGITS
    navigationItem
    0.83
    viewWillAppear
    0.81
    UIControlState
    0.75
    UITableView
    0.74
    UIImage
    0.73
    UIImageView
    0.71
    collectionView
    0.69
    NSUserDefaults
    0.69
    navigationBar
    0.69
    NSDate
    0.69
    Activations Density 10.762%

    No Known Activations