© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 4883
    Prev
    Next
    INDEX
    Explanations

    particles (in, to, of, from) and possibly also some Arabic words

    oai_token-act-pair · gemini-2.0-flash

    non-English words and locations

    np_max-act-logits · 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
     $_"
    -1.09
     Efq
    -1.06
    MigrationBuilder
    -1.03
     photolibrary
    -1.02
     AppColors
    -1.01
     itſelf
    -1.01
     IBRARY
    -1.00
     Theſe
    -0.95
     ARXIV
    -0.94
     NDEBUG
    -0.94
    POSITIVE LOGITS
    get
    0.28
    (
    0.26
    of
    0.24
    <eos>
    0.24
    ,
    0.24
    str
    0.23
    v
    0.23
    ...
    0.23
    di
    0.23
    for
    0.23
    Activations Density 0.119%

    No Known Activations