© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 13337
    Prev
    Next
    INDEX
    Explanations

    words that start with "ter"

    oai_token-act-pair · gemini-2.0-flash

    terms related to the prefix "Ter"

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

    Ter

    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
     متعلقه
    -0.97
    parsedMessage
    -0.94
     resourceCulture
    -0.78
    SharedCtor
    -0.75
     kasarigan
    -0.73
    CloseOperation
    -0.70
    oneofs
    -0.69
     فريبيس
    -0.68
     intStringLen
    -0.67
    EDEFAULT
    -0.65
    POSITIVE LOGITS
    InitStruct
    0.45
     COPYRIGHT
    0.43
    GEBURTSDATUM
    0.42
    квар
    0.41
     vergessen
    0.41
    ekš
    0.40
    перь
    0.40
    dema
    0.40
    千里
    0.40
    apper
    0.40
    Activations Density 0.278%

    No Known Activations