© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 6135
    Prev
    Next
    INDEX
    Explanations

    general-purpose words that come before or after prepositions

    oai_token-act-pair · gemini-2.0-flash

    Technical/formal language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    intios
    -0.66
    Földrajzportál
    -0.51
    WithEmail
    -0.49
     urbana
    -0.47
     devoirs
    -0.46
    URLException
    -0.46
     quiera
    -0.46
     financières
    -0.45
     lenker
    -0.45
     humaines
    -0.45
    POSITIVE LOGITS
    SBATCH
    0.69
     AssemblyTitle
    0.68
    <bos>
    0.61
     JADX
    0.61
     EdgeInsets
    0.57
    stdc
    0.55
    kloped
    0.54
     disponibilités
    0.54
     readers
    0.52
    ErrUnexpectedEOF
    0.52
    Activations Density 7.136%

    No Known Activations