© 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. 8529
    Prev
    Next
    INDEX
    Explanations

    instances of the word "control" and options to control something, especially by the user.

    oai_token-act-pair · gemini-2.0-flash

    Instructions

    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
     Register
    -0.69
     Leverage
    -0.58
     Consume
    -0.57
    Register
    -0.56
     Ebert
    -0.56
     Navig
    -0.54
    posedge
    -0.53
    preventDefault
    -0.52
    executed
    -0.52
     BoxDecoration
    -0.52
    POSITIVE LOGITS
    ViewFeatures
    0.59
    WithIOException
    0.56
    లాలు
    0.54
    YourGuide
    0.50
    chyma
    0.49
    ++
    0.49
    cotch
    0.49
    허
    0.49
    velocityX
    0.48
    rativa
    0.48
    Activations Density 5.678%

    No Known Activations