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. 14446
    Prev
    Next
    INDEX
    Explanations

    words that follow or are variations of the verb "to be"

    oai_token-act-pair · gemini-2.0-flash

    formal announcements

    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
    مصادر
    -0.73
     ComVisible
    -0.68
    ContentAlignment
    -0.67
     VizieR
    -0.67
    ReusableCell
    -0.65
    gonic
    -0.65
    toBeTruthy
    -0.63
    Facades
    -0.63
    cshtml
    -0.62
     getItemCount
    -0.61
    POSITIVE LOGITS
     CreateTagHelper
    0.52
    roquia
    0.43
    ưng
    0.42
    XXIV
    0.41
     smer
    0.40
     asked
    0.40
     immor
    0.40
    ówek
    0.40
     standing
    0.39
    Derp
    0.39
    Activations Density 0.770%

    No Known Activations