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. 20-GEMMASCOPE-TRANSCODER-16K
    4. 14315
    Prev
    Next
    INDEX
    Explanations

    email addresses

    oai_token-act-pair · gemini-2.0-flash

    say @

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    @
    -0.86
     @
    -0.71
    ↵↵
    -0.63
    ,
    -0.63
    ↵
    -0.63
    .
    -0.63
     A
    -0.62
     ,
    -0.60
     I
    -0.59
    ?
    -0.58
    POSITIVE LOGITS
     Efq
    1.23
     myſelf
    1.18
     AssemblyCulture
    1.17
    ſelves
    1.07
     uſed
    1.06
     itſelf
    1.05
     Majefty
    1.02
    tagHelperRunner
    1.01
     betweenstory
    1.00
     houſe
    0.99
    Activations Density 0.346%

    No Known Activations