© 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. 5565
    Prev
    Next
    INDEX
    Explanations

    prepositions typically used in scientific writing

    oai_token-act-pair · gemini-2.0-flash

    temporal expressions

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

    units of time

    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
    +#+#
    -0.46
     först
    -0.44
     rendez
    -0.44
     Makefile
    -0.44
     first
    -0.43
    itiés
    -0.43
     firft
    -0.43
     primeiras
    -0.42
     مرئيه
    -0.42
     comets
    -0.41
    POSITIVE LOGITS
     Day
    2.09
     day
    2.06
    Day
    1.78
     DAY
    1.75
    day
    1.62
     week
    1.53
    DAY
    1.43
     Week
    1.40
     Month
    1.29
     month
    1.28
    Activations Density 4.827%

    No Known Activations