Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-GEMMASCOPE-TRANSCODER-16K
    4. 7285
    Prev
    Next
    INDEX
    Explanations

    mentions of abstract concepts, particularly related to plans or theories

    oai_token-act-pair · gemini-2.0-flash

    idea

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     idea
    -1.34
     result
    -1.34
     fact
    -1.34
     way
    -1.32
     possibility
    -1.30
     situation
    -1.28
     question
    -1.22
     reason
    -1.20
     conclusion
    -1.15
     notion
    -1.13
    POSITIVE LOGITS
     pareti
    0.87
     braccia
    0.85
     tasche
    0.84
     elettrico
    0.84
    LookAnd
    0.83
     petto
    0.81
     devenus
    0.80
     gambe
    0.79
     bonté
    0.77
     situés
    0.77
    Activations Density 3.443%

    No Known Activations