© 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. 24-GEMMASCOPE-TRANSCODER-16K
    4. 3213
    Prev
    Next
    INDEX
    Explanations

    the word "from" and place names, often in combination with other location-related terms like "United" and "Kingdom".

    oai_token-act-pair · gemini-2.0-flash

    United Kingdom

    np_max-act-logits · gemini-2.0-flash

    United

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     firebaseConfig
    -0.70
    SharedDtor
    -0.68
     Audiodateien
    -0.68
     British
    -0.67
     NSCoder
    -0.66
     BRITISH
    -0.65
    British
    -0.65
    Tikang
    -0.59
     british
    -0.58
     betweenstory
    -0.56
    POSITIVE LOGITS
     Great
    2.89
    Great
    2.63
    GREAT
    2.11
     GREAT
    1.99
    great
    1.70
     great
    1.38
     Gt
    1.22
    TheGreat
    1.16
     Вели
    1.15
     Grande
    1.13
    Activations Density 3.431%

    No Known Activations