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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 16157
    Prev
    Next
    INDEX
    Explanations

    the word "writing" and the phrase "black hole"

    oai_token-act-pair · gemini-2.0-flash

    writing

    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
     صوتيه
    -0.94
    Literatuur
    -0.85
     itſelf
    -0.83
    InputBorder
    -0.82
     vectorielles
    -0.82
     étoit
    -0.81
    StoryboardSegue
    -0.80
     Efq
    -0.80
     électroniques
    -0.79
     مرئيه
    -0.79
    POSITIVE LOGITS
    <eos>
    0.67
    的
    0.57
    ,
    0.56
    一
    0.55
    ↵↵↵
    0.55
    s
    0.55
    余
    0.52
    Від
    0.51
     ;
    0.50
     He
    0.49
    Activations Density 0.324%

    No Known Activations