© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5653
    Prev
    Next
    INDEX
    Explanations

    sentences that contain the word 'has' followed by a verb or preposition

    oai_token-act-pair · gemini-2.0-flash

    phrases indicating approximation or estimates

    np_token-act-pair-logits · gpt-4o-mini

    nearly

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     betweenstory
    -0.63
    CompleteListener
    -0.63
    WebVitals
    -0.59
    imageshack
    -0.48
    contentLoaded
    -0.48
    Notae
    -0.47
    leetcode
    -0.45
    ceğini
    -0.45
    EndOf
    -0.44
    ForResult
    -0.44
    POSITIVE LOGITS
     virš
    0.79
     more
    0.75
     nigh
    0.72
     nearly
    0.70
    NEAR
    0.70
     about
    0.69
    RUnlock
    0.69
     close
    0.68
     itſelf
    0.67
     almost
    0.66
    Activations Density 2.022%

    No Known Activations