© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 10457
    Prev
    Next
    INDEX
    Explanations

    the string "filename"

    oai_token-act-pair · gemini-2.0-flash

    filename

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     seguente
    -0.71
     viață
    -0.65
     vícti
    -0.63
     obicei
    -0.61
     ordinaires
    -0.60
     particolare
    -0.60
     conoscere
    -0.59
     scattata
    -0.59
     betreft
    -0.59
     résulte
    -0.59
    POSITIVE LOGITS
     незавершена
    1.02
    StoryboardSegue
    0.90
     Савезне
    0.85
    WebVitals
    0.84
     ProtoMessage
    0.84
    IUrlHelper
    0.83
    LookAnd
    0.81
     CreateTagHelper
    0.79
    webElementXpaths
    0.77
    /***/
    0.76
    Activations Density 1.377%

    No Known Activations