© 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. 4766
    Prev
    Next
    INDEX
    Explanations

    words related to the validity, conditions, and results of a study

    oai_token-act-pair · gemini-2.0-flash

    the word "hold"

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

    hold

    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
    #+#
    -0.69
    aarrggbb
    -0.61
    cèse
    -0.60
     ExecuteAsync
    -0.56
    HasForeignKey
    -0.55
    ISupport
    -0.55
     infarction
    -0.54
     المعيارى
    -0.54
    copg
    -0.54
    terase
    -0.54
    POSITIVE LOGITS
     hold
    2.47
     holds
    2.38
     holding
    2.19
     Hold
    2.11
    hold
    2.09
     Holds
    2.00
     HOLD
    1.98
    Hold
    1.95
     held
    1.93
    holds
    1.88
    Activations Density 4.782%

    No Known Activations