© 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
    3. Gemma-2-2B
    5. 3-GEMMASCOPE-TRANSCODER-16K
    7. 8719
    Prev
    Next
    INDEX
    Explanations

    Java source code

    oai_token-act-pair · gemini-2.0-flash

    my

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    my
    -1.45
    My
    -1.30
    MY
    -1.23
     My
    -1.13
     MY
    -1.07
     my
    -1.00
    getMy
    -0.84
    mys
    -0.75
     meu
    -0.72
    Моя
    -0.68
    POSITIVE LOGITS
    AddTagHelper
    0.77
    ValueStyle
    0.72
    RetentionPolicy
    0.71
    AnchorStyles
    0.71
    Geplaatst
    0.71
    ContentAsync
    0.69
    
    0.68
    ecap
    0.65
    LayoutConstraint
    0.65
     disambiguazione
    0.65
    Activations Density 1.608%

    No Known Activations