© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6594
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to mobile devices, e-readers, and associated brands like "Kindle", "Android", and "Blackberry".

    oai_token-act-pair · gemini-2.0-flash

    terms related to technology and devices

    np_token-act-pair-logits · gpt-4o-mini

    Online/Offline

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     ویکی‌پدیای
    -0.93
     AssemblyCulture
    -0.92
    AddTagHelper
    -0.85
    MessageTagHelper
    -0.84
     Normdatei
    -0.84
     NSCoder
    -0.83
    ArgsConstructor
    -0.81
    GEBURTSDATUM
    -0.80
     estekak
    -0.80
     HasFactory
    -0.79
    POSITIVE LOGITS
     offline
    0.51
     OS
    0.46
    OS
    0.46
     off
    0.46
    off
    0.45
    omla
    0.44
    connect
    0.43
     online
    0.42
     emb
    0.42
    Online
    0.42
    Activations Density 2.205%

    No Known Activations