© 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. 12365
    Prev
    Next
    INDEX
    Explanations

    texts about advertisement

    oai_token-act-pair · gemini-2.0-flash

    terms related to special offers or promotions

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

    foreign words

    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
    kháu
    -0.64
    DebuggerStep
    -0.60
     الرياضيه
    -0.58
    IUrlHelper
    -0.56
     Vikipedi
    -0.56
     plenary
    -0.56
    twimg
    -0.55
    numerusform
    -0.54
     /\.
    -0.53
    RTLD
    -0.53
    POSITIVE LOGITS
     linkovi
    0.55
    oucí
    0.52
    velles
    0.49
     ask
    0.47
     existencia
    0.45
     call
    0.44
    ########.
    0.43
    pragma
    0.43
    τή
    0.43
    lenül
    0.42
    Activations Density 3.070%

    No Known Activations