© 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. 9080
    Prev
    Next
    INDEX
    Explanations

    words and phrases suggesting progress or benefits

    oai_token-act-pair · gemini-2.0-flash

    Creating positive change

    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
    EndGlobalSection
    -0.62
    mobileqq
    -0.56
    ագրություններ
    -0.56
    ̍
    -0.54
     المعيارى
    -0.54
    IndentedString
    -0.52
     saites
    -0.52
     '\\;'
    -0.52
     мәкал
    -0.49
     ComVisible
    -0.48
    POSITIVE LOGITS
    出版年
    0.61
     hjemme
    0.58
    Kaieteur
    0.56
    لكتر
    0.56
    AddTagHelper
    0.54
    andina
    0.54
    ligg
    0.53
     estimés
    0.53
     Brind
    0.53
    brainly
    0.53
    Activations Density 10.472%

    No Known Activations