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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 12129
    Prev
    Next
    INDEX
    Explanations

    the word "is" preceded by specific pronouns or related to discussing the reason of being for a company or purpose

    oai_token-act-pair · gemini-2.0-flash

    variations of the word 'build'

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

    built

    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
    تفصیلات
    -0.55
    Portale
    -0.53
     aload
    -0.50
    ưới
    -0.49
     tasche
    -0.48
    Tazama
    -0.48
     chi̍t
    -0.47
     useDispatch
    -0.47
     parlent
    -0.45
    烷
    -0.45
    POSITIVE LOGITS
     built
    1.41
    built
    1.26
    Built
    1.21
     Built
    1.20
     rests
    1.11
     based
    1.08
     resting
    1.08
     riding
    1.05
     build
    1.05
     rest
    1.05
    Activations Density 2.756%

    No Known Activations