© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 16052
    Prev
    Next
    INDEX
    Explanations

    the word "highly", and to a lesser extent also finds words appearing near "highly"

    oai_token-act-pair · gemini-2.0-flash

    highly

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    awaiter
    -0.77
    انتهای
    -0.63
    حياتها
    -0.63
    autoreleasepool
    -0.63
     Partagez
    -0.62
    jaardag
    -0.60
    évaluateur
    -0.60
    IContainer
    -0.60
    حياته
    -0.58
     Rptr
    -0.57
    POSITIVE LOGITS
    unik
    0.51
     Réponses
    0.45
    BOA
    0.43
     uncon
    0.43
    cite
    0.43
     estimés
    0.41
    Referințe
    0.41
    Ur
    0.39
    cove
    0.39
     Pam
    0.39
    Activations Density 1.040%

    No Known Activations