© 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. 3645
    Prev
    Next
    INDEX
    Explanations

    instances where a user is making a suggestion or recommendation

    oai_token-act-pair · gemini-2.0-flash

    actions related to suggestions or recommendations

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

    recommend/suggest

    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
     recommend
    -0.68
     suggest
    -0.63
     recommended
    -0.63
     sugger
    -0.62
     recommendation
    -0.55
     raccomand
    -0.55
     recomend
    -0.51
     RECOMMENDED
    -0.50
     recommends
    -0.50
     Suggestion
    -0.50
    POSITIVE LOGITS
     putting
    0.85
     treating
    0.82
     bringing
    0.79
     adding
    0.78
     deleting
    0.78
     ignoring
    0.76
     creating
    0.76
     taking
    0.74
     removing
    0.73
     combining
    0.73
    Activations Density 4.948%

    No Known Activations