© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 7348
    Prev
    Next
    INDEX
    Explanations

    phrases encouraging user engagement

    oai_token-act-pair · gemini-2.0-flash

    variations of the word "keep"

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

    keep

    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
     Audiodateien
    -0.76
    abestanden
    -0.70
    PreExecute
    -0.66
    ParallelGroup
    -0.63
    endpush
    -0.63
     gynhyrchwyd
    -0.62
    httphttps
    -0.61
     AssemblyCulture
    -0.60
    FieldBuilder
    -0.60
    Искәрмәләр
    -0.59
    POSITIVE LOGITS
     keep
    2.53
     kept
    2.47
     keeping
    2.42
    Keep
    2.41
    keep
    2.39
     keeps
    2.36
     Keep
    2.36
     Keeping
    2.25
    Keeping
    2.19
    KEEP
    2.09
    Activations Density 2.079%

    No Known Activations