© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 11689
    Prev
    Next
    INDEX
    Explanations

    partial spelling of words that include `am`, `os`, `il`, `ib`, um, or `ood` and also a stray `good`

    oai_token-act-pair · 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
    aw
    -0.66
    ace
    -0.62
    av
    -0.61
    ake
    -0.60
    ach
    -0.60
    am
    -0.60
    a
    -0.59
    ain
    -0.59
    ak
    -0.57
    able
    -0.56
    POSITIVE LOGITS
     Reverso
    0.56
    ousine
    0.55
    orphic
    0.54
    inique
    0.54
    idate
    0.53
    istik
    0.52
    phors
    0.52
    abinieri
    0.51
    atosis
    0.51
    andescent
    0.50
    Activations Density 6.305%

    No Known Activations