© 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
    2. Gemma-2-2B
    3. 24-GEMMASCOPE-TRANSCODER-16K
    4. 9054
    Prev
    Next
    INDEX
    Explanations

    the word "sand" and words relating to geography and topography

    oai_token-act-pair · gemini-2.0-flash

    sand

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    Geplaatst
    -0.91
     Reſ
    -0.83
     Majefty
    -0.77
     Chriftian
    -0.76
     Monfieur
    -0.76
     purpoſe
    -0.72
     ſtand
    -0.72
     perſon
    -0.72
     Anſ
    -0.71
     Roskov
    -0.70
    POSITIVE LOGITS
    gate
    0.42
    Personensuche
    0.41
     Waray
    0.40
    [...,
    0.40
    //
    0.40
    melidir
    0.40
    flam
    0.39
    fund
    0.39
    ThroughAttribute
    0.39
    mittee
    0.38
    Activations Density 2.534%

    No Known Activations