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. 0-GEMMASCOPE-TRANSCODER-16K
    4. 7310
    Prev
    Next
    INDEX
    Explanations

    the word "serial" or words associated with emotions.

    oai_token-act-pair · gemini-2.0-flash

    mood, serial

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     épaules
    -0.67
    ↵↵
    -0.65
     istor
    -0.63
    <eos>
    -0.60
     travailleurs
    -0.60
    。
    -0.58
    Lw
    -0.58
     picioare
    -0.57
     écrans
    -0.57
     spurious
    -0.57
    POSITIVE LOGITS
    ]--;
    0.94
     ſind
    0.82
    Pautan
    0.82
    UrlResolution
    0.79
     tartalomajánló
    0.77
    RenderAtEndOf
    0.77
    =$?
    0.77
    pportun
    0.76
     betweenstory
    0.75
    ConstraintMaker
    0.75
    Activations Density 0.686%

    No Known Activations