© 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
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5494
    Prev
    Next
    INDEX
    Explanations

    phrases describing negative or challenging situations

    oai_token-act-pair · gemini-2.0-flash

    the concept of depth

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

    deep

    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
     '\\;'
    -0.89
    UnusedPrivate
    -0.80
     Baillargeon
    -0.80
    mybatisplus
    -0.78
    +#+#
    -0.78
    Autoritní
    -0.77
    Biographie
    -0.76
    Diweddarwch
    -0.76
     Normdatei
    -0.75
    AddTagHelper
    -0.75
    POSITIVE LOGITS
     deep
    0.73
     funk
    0.63
     hole
    0.60
     DEEP
    0.56
     deeper
    0.56
    deep
    0.55
    深い
    0.52
    深く
    0.50
     profondo
    0.49
     deepest
    0.49
    Activations Density 1.170%

    No Known Activations