© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 11874
    Prev
    Next
    INDEX
    Explanations

    the word "the" or capitalized months followed by numbers expressing years, possibly in hyphenated ranges

    oai_token-act-pair · gemini-2.0-flash

    Mentions dates/time periods

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    InjectAttribute
    -0.77
     fall
    -0.73
     first
    -0.71
     last
    -0.69
    IUrlHelper
    -0.64
     Fall
    -0.63
     Last
    -0.63
    Fall
    -0.62
     following
    -0.62
     final
    -0.62
    POSITIVE LOGITS
    Past
    0.93
     past
    0.93
     Past
    0.85
    past
    0.82
     PAST
    0.73
    PAST
    0.70
     onResponse
    0.45
     Vergangenheit
    0.45
     Drapeau
    0.44
     pasado
    0.44
    Activations Density 3.874%

    No Known Activations