© 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. 12012
    Prev
    Next
    INDEX
    Explanations

    keys that are common in json-like data structures

    oai_token-act-pair · gemini-2.0-flash

    formatting or metadata labels

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

    last

    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
    zunehmen
    -0.59
     Exacts
    -0.56
    ]<<
    -0.54
     MNRAS
    -0.53
    topbar
    -0.51
     defaultstate
    -0.50
    principalTable
    -0.50
    Ekster
    -0.49
     împre
    -0.49
     jedin
    -0.49
    POSITIVE LOGITS
    CHAR
    0.63
     char
    0.59
     استنادى
    0.54
    İstinadlar
    0.54
     CHAR
    0.54
    RegistryLite
    0.52
    Char
    0.51
    GEBURTSDATUM
    0.50
    char
    0.50
     dente
    0.50
    Activations Density 3.239%

    No Known Activations