© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 998
    Prev
    Next
    INDEX
    Explanations

    terms related to academic papers and technical documentation

    oai_token-act-pair · gemini-2.0-flash

    Section titles

    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
    +#+#
    -0.66
    hoeddwyd
    -0.59
    findpost
    -0.54
    CONCURRENT
    -0.52
    Jîn
    -0.52
     للاسماء
    -0.51
    TagMode
    -0.50
    IUrlHelper
    -0.49
     memp
    -0.48
     kasarigan
    -0.48
    POSITIVE LOGITS
     And
    0.73
     Of
    0.72
    And
    0.66
     **/
    
    0.61
     About
    0.61
    Of
    0.60
    Δείτε
    0.57
     发表于
    0.57
     Theorems
    0.56
     】
    0.56
    Activations Density 21.984%

    No Known Activations