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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 22-GEMMASCOPE-TRANSCODER-16K
    4. 14442
    Prev
    Next
    INDEX
    Explanations

    words related to the conjunction and preposition "to"

    oai_token-act-pair · gemini-2.0-flash

    and, comma

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    <bos>
    -0.71
     raiſ
    -0.69
     africaine
    -0.63
     setti
    -0.58
     poffe
    -0.57
     zijne
    -0.57
     pleaf
    -0.55
     bathing
    -0.55
     exceptionnelle
    -0.55
    )))),
    -0.53
    POSITIVE LOGITS
     edit
    1.05
     build
    0.99
     install
    0.98
     sell
    0.98
     fill
    0.96
     move
    0.96
     bake
    0.96
     isolate
    0.96
     kill
    0.96
     eat
    0.95
    Activations Density 7.320%

    No Known Activations