© 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. 15662
    Prev
    Next
    INDEX
    Explanations

    code snippets

    oai_token-act-pair · gemini-2.0-flash

    Code and other languages

    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
    CloseOperation
    -0.81
     beſch
    -0.79
    sizeCache
    -0.79
    SourceChecksum
    -0.78
     ISNI
    -0.78
     erſt
    -0.78
     picioare
    -0.77
     témoig
    -0.77
     Dieſe
    -0.77
    <unused57>
    -0.76
    POSITIVE LOGITS
     itu
    -0.01
     ako
    -0.01
     uma
    -0.01
     presenti
    -0.02
    私は
    -0.03
     ini
    -0.03
     een
    -0.03
     und
    -0.03
     como
    -0.03
     eure
    -0.03
    Activations Density 4.492%

    No Known Activations