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. 21-GEMMASCOPE-TRANSCODER-16K
    4. 11201
    Prev
    Next
    INDEX
    Explanations

    expressions of mathematical subtraction and negation with a dash

    oai_token-act-pair · gemini-2.0-flash

    technical or specialized terms

    np_token-act-pair-logits · gpt-4o-mini

    dash

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     something
    -1.09
     Something
    -1.00
    Something
    -0.98
    something
    -0.93
     SOMETHING
    -0.80
     iets
    -0.77
     algo
    -0.75
     qualcosa
    -0.74
     somethin
    -0.72
     ceva
    -0.70
    POSITIVE LOGITS
    ImageContext
    0.52
    
    0.47
    celes
    0.46
     IConfiguration
    0.46
    rungsseite
    0.46
    🏾
    0.46
    IonicModule
    0.45
    🏿
    0.44
    PKCS
    0.44
    ⃗
    0.43
    Activations Density 4.020%

    No Known Activations