© 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. 2561
    Prev
    Next
    INDEX
    Explanations

    articles "a" and "an" as well as certain common grammatical words like "the", "was", and "to".

    oai_token-act-pair · gemini-2.0-flash

    scientific/medical information

    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
    anskje
    -0.66
    enapa
    -0.62
    iffance
    -0.61
    endorong
    -0.59
    tymologie
    -0.59
    ientôt
    -0.58
    ésult
    -0.56
    akaian
    -0.55
    iffion
    -0.55
    ulongan
    -0.54
    POSITIVE LOGITS
    led
    1.11
    es
    1.09
    os
    1.07
    gs
    1.05
    ed
    1.05
    cs
    1.05
    op
    1.05
    res
    1.04
    ded
    1.04
    hed
    1.03
    Activations Density 20.376%

    No Known Activations