© 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. 7981
    Prev
    Next
    INDEX
    Explanations

    a variety of proper nouns, including organizations, people, and musical artists, as well as colons followed by explanations.

    oai_token-act-pair · 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
    iffance
    -1.23
    amaño
    -1.13
    ethene
    -1.08
    tiérrez
    -1.05
     Efq
    -1.02
    Abitanti
    -1.02
    LookAnd
    -1.01
     meriva
    -0.98
     ARXIV
    -0.98
    ipheral
    -0.98
    POSITIVE LOGITS
    TO
    0.79
    ds
    0.77
    TE
    0.75
    SE
    0.74
    RR
    0.73
    CH
    0.71
    AH
    0.71
    IS
    0.71
    SH
    0.71
    DS
    0.71
    Activations Density 3.988%

    No Known Activations