© 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. 1154
    Prev
    Next
    INDEX
    Explanations

    various Python syntax elements like periods, underscores, brackets, and conditional statements within code snippets.

    oai_token-act-pair · gemini-2.0-flash

    programming 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
     الحره
    -0.70
     linkovi
    -0.68
     defense
    -0.66
     Defense
    -0.65
     برانيه
    -0.61
     #
    -0.59
     Défense
    -0.59
    Defense
    -0.58
     defence
    -0.56
    Defence
    -0.56
    POSITIVE LOGITS
    ingtones
    0.59
    stories
    0.59
    energies
    0.58
    centroids
    0.57
    Specifier
    0.57
    arrows
    0.55
    Halaman
    0.55
     
    0.54
    []
    0.54
    quations
    0.53
    Activations Density 6.947%

    No Known Activations