© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 13118
    Prev
    Next
    INDEX
    Explanations

    mentions of frequency and groups/species, by keying off of "most", "people", "species", "mammals", etc.

    oai_token-act-pair · gemini-2.0-flash

    most

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     most
    -0.85
     Most
    -0.85
    most
    -0.73
    Most
    -0.70
     MOST
    -0.64
    MOST
    -0.55
     Many
    -0.53
    <eos>
    -0.53
     many
    -0.52
    大部分
    -0.50
    POSITIVE LOGITS
     reaſon
    0.82
     pleaſure
    0.81
     doubtnut
    0.81
     houſe
    0.81
     $_"
    0.80
     purpoſe
    0.79
     Monfieur
    0.79
     Reſ
    0.79
    ſelves
    0.78
     precedent
    0.77
    Activations Density 4.124%

    No Known Activations