© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 4811
    Prev
    Next
    INDEX
    Explanations

    mixed Spanish and English related to disabling keys in a database table and about VPNs

    oai_token-act-pair · gemini-2.0-flash

    una

    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
    FormBorderStyle
    -0.44
    helial
    -0.43
     Tray
    -0.43
    ionage
    -0.41
    toggler
    -0.40
     cardinals
    -0.40
     оригіналу
    -0.40
     tray
    -0.40
     chod
    -0.40
    égard
    -0.40
    POSITIVE LOGITS
    protoimpl
    0.69
    Билгалдахарш
    0.68
     fasse
    0.66
    windowFixed
    0.65
     contactez
    0.63
    wiſe
    0.63
     sélectionnez
    0.62
    ſelves
    0.61
    تقاوى
    0.60
     Accesat
    0.60
    Activations Density 0.618%

    No Known Activations