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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12568
    Prev
    Next
    INDEX
    Explanations

    code snippets and references to function definitions, particularly in Swift

    oai_token-act-pair · gemini-2.0-flash

    Did

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     isComment
    -0.46
     understatement
    -0.46
     coö
    -0.45
     stimmt
    -0.45
     correct
    -0.45
     Oui
    -0.45
    ']));
    -0.44
     anthrop
    -0.44
     experiment
    -0.44
     circum
    -0.44
    POSITIVE LOGITS
     незавершена
    0.89
     NSCoder
    0.87
     onCreateView
    0.79
    AutoScale
    0.77
    OGND
    0.77
     calendriers
    0.76
     téléphonique
    0.74
     صوتيه
    0.69
     onOptions
    0.68
     Normdatei
    0.67
    Activations Density 1.256%

    No Known Activations