© 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. 16161
    Prev
    Next
    INDEX
    Explanations

    the word "the" preceded by a number

    oai_token-act-pair · gemini-2.0-flash

    the

    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
    +)$
    -0.61
    jspb
    -0.52
    %"),
    -0.49
    yves
    -0.47
     Why
    -0.46
    }());
    -0.44
    ilmente
    -0.44
    WHY
    -0.43
    Why
    -0.43
     WHY
    -0.43
    POSITIVE LOGITS
     nice
    1.24
    nice
    0.88
    Nice
    0.82
     Nice
    0.75
     great
    0.72
    ImageContext
    0.71
    Atsauces
    0.70
     lovely
    0.70
    TagMode
    0.69
    StoryboardSegue
    0.64
    Activations Density 1.658%

    No Known Activations