© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 15835
    Prev
    Next
    INDEX
    Explanations

    words related to paleontology and taxonomy, especially names of extinct species

    oai_token-act-pair · gemini-2.0-flash

    scientific and technical documents

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     springfox
    -0.84
    ArgsConstructor
    -0.73
    IsContent
    -0.60
     nakalista
    -0.59
    igshid
    -0.58
    లాలు
    -0.57
     Inflate
    -0.57
    ----</
    -0.56
     &___
    -0.56
    FundMe
    -0.54
    POSITIVE LOGITS
     sph
    0.53
     виправивши
    0.49
    EXTERN
    0.48
     australis
    0.47
     doubl
    0.47
     Sph
    0.46
     lattices
    0.46
     lattice
    0.45
    lamy
    0.45
    frame
    0.45
    Activations Density 3.963%

    No Known Activations