© 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. 15992
    Prev
    Next
    INDEX
    Explanations

    code snippets, file paths, and diff outputs

    oai_token-act-pair · gemini-2.0-flash

    Code diffs

    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
     BF
    -0.71
    D
    -0.68
    B
    -0.67
     d
    -0.67
     b
    -0.65
    BF
    -0.63
    F
    -0.63
    FD
    -0.63
    BD
    -0.62
    DF
    -0.60
    POSITIVE LOGITS
    ValueGeneration
    0.62
     titolata
    0.60
     étoit
    0.58
    TestTools
    0.56
     vectorielles
    0.54
     journalistes
    0.54
     vectorielle
    0.52
     pouvoit
    0.52
     avoient
    0.52
     propriétaires
    0.51
    Activations Density 14.174%

    No Known Activations