© 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. 5686
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to terms and conditions, money, and measurement

    oai_token-act-pair · gemini-2.0-flash

    code snippets

    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
     creation
    -1.45
     removal
    -1.34
     formation
    -1.34
    creation
    -1.31
     detection
    -1.28
     Removal
    -1.27
    Creation
    -1.26
     Creation
    -1.25
     completion
    -1.23
     implementation
    -1.23
    POSITIVE LOGITS
     planète
    0.48
     سكانية
    0.47
     monnaie
    0.47
     itemprop
    0.43
    enumii
    0.42
     désolés
    0.41
     varargin
    0.40
    ercito
    0.40
    matchCondition
    0.40
     חיצוניים
    0.40
    Activations Density 4.209%

    No Known Activations