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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3696
    Prev
    Next
    INDEX
    Explanations

    sentences that are making definitive statements, using a broad range of words

    oai_token-act-pair · gemini-2.0-flash

    variations of "only"

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

    verb "to be"

    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
    ]--;
    -0.76
     calendriers
    -0.71
    ReusableCell
    -0.69
     AssemblyCulture
    -0.63
    SequentialGroup
    -0.63
    ]='\
    -0.60
     initComponents
    -0.60
     CURIAM
    -0.59
    avras
    -0.59
     通販
    -0.57
    POSITIVE LOGITS
     only
    3.05
    only
    2.72
    Only
    2.59
     Only
    2.45
    ONLY
    2.19
     ONLY
    2.14
     только
    1.96
     seulement
    1.84
     tylko
    1.79
     тільки
    1.66
    Activations Density 3.711%

    No Known Activations