© 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. 15016
    Prev
    Next
    INDEX
    Explanations

    uses of the word "apply" and related words like "state" and file.

    oai_token-act-pair · gemini-2.0-flash

    legal/official procedures

    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
     permanent
    -0.75
     automatic
    -0.75
    automatic
    -0.73
    permanent
    -0.72
     positive
    -0.71
     constant
    -0.71
     professional
    -0.71
     indirect
    -0.70
     ethical
    -0.69
     practical
    -0.69
    POSITIVE LOGITS
     propOrder
    0.63
    IUrlHelper
    0.61
    featureID
    0.57
     contextLoads
    0.57
     Италијани
    0.56
     <=",
    0.54
     Obispo
    0.54
    OrBuilder
    0.54
    parsedMessage
    0.52
     ToString
    0.52
    Activations Density 4.866%

    No Known Activations