© 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. 2362
    Prev
    Next
    INDEX
    Explanations

    references to figures, tables, and supplementary materials in research papers

    oai_token-act-pair · gemini-2.0-flash

    File references

    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
     pleaſure
    -0.54
     Intuition
    -0.50
     Majefty
    -0.50
     betweenstory
    -0.49
     Monfieur
    -0.49
     ſever
    -0.48
     intuition
    -0.48
    fromnode
    -0.47
     natu
    -0.47
     uſed
    -0.47
    POSITIVE LOGITS
    WriteBarrier
    0.61
     arşivlendi
    0.54
    OCA
    0.54
    TF
    0.54
    ?}",
    0.53
    =]
    0.53
    tură
    0.52
    MHz
    0.51
    trc
    0.51
    bps
    0.50
    Activations Density 28.756%

    No Known Activations