© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 3243
    Prev
    Next
    INDEX
    Explanations

    words and phrases heavily related to programming, code examples and descriptions of code

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    Попис
    -0.93
     nakalista
    -0.91
     مشين
    -0.89
     صوتيه
    -0.85
    AddTagHelper
    -0.79
    AccessorTable
    -0.78
    出版年
    -0.78
    featureID
    -0.77
    Demografie
    -0.75
     تانيه
    -0.75
    POSITIVE LOGITS
     ense
    0.35
    eventbus
    0.35
     mol
    0.32
    COLLE
    0.32
    קד
    0.32
     len
    0.31
    iter
    0.31
     Mol
    0.30
    ücken
    0.30
     kong
    0.30
    Activations Density 0.259%

    No Known Activations