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. 23-GEMMASCOPE-TRANSCODER-16K
    4. 12185
    Prev
    Next
    INDEX
    Explanations

    the word "went" or "go" in association with career trajectory

    oai_token-act-pair · gemini-2.0-flash

    go

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    tand
    -0.66
    AMED
    -0.65
    thmetic
    -0.64
     Akismet
    -0.63
    unately
    -0.61
    iffance
    -0.60
    colage
    -0.59
    ^(@)
    -0.58
    ibatis
    -0.57
    ρίς
    -0.57
    POSITIVE LOGITS
    IntoConstraints
    0.60
     MessageBoxIcon
    0.51
    MessageState
    0.50
    Personensuche
    0.47
    RTLD
    0.45
     utafitiHapana
    0.44
     Италијани
    0.42
    ti
    0.42
     vuitton
    0.42
     transférez
    0.41
    Activations Density 0.647%

    No Known Activations