© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 7997
    Prev
    Next
    INDEX
    Explanations

    general english words that are commonly used

    oai_token-act-pair · gemini-2.0-flash

    got

    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
     angef
    -0.40
    Manbalar
    -0.40
    openqa
    -0.40
    arg
    -0.38
     madrugada
    -0.36
     Super
    -0.36
     terres
    -0.36
    1
    -0.35
     Comparative
    -0.35
    ()].
    -0.35
    POSITIVE LOGITS
     itſelf
    0.84
    IUrlHelper
    0.81
    ValueStyle
    0.79
     myſelf
    0.77
    InjectAttribute
    0.76
    posedge
    0.76
    ſelves
    0.75
    ſelf
    0.75
    TestingModule
    0.75
    onedDateTime
    0.75
    Activations Density 11.754%

    No Known Activations