© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 13961
    Prev
    Next
    INDEX
    Explanations

    tokens from Indonesian text

    oai_token-act-pair · gemini-2.0-flash

    Informal text and code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    ]--;
    -0.90
    contentLoaded
    -0.86
    ]")]
    -0.80
     disambiguazione
    -0.77
     متعلقه
    -0.72
     ExecuteAsync
    -0.71
     onCancelled
    -0.68
    )\}$
    -0.67
    --]
    -0.67
     typelib
    -0.67
    POSITIVE LOGITS
    ellschaft
    0.56
    wan
    0.44
     Waren
    0.44
    choc
    0.42
    tente
    0.41
     uter
    0.41
    ampi
    0.41
    AndEndTag
    0.40
     am
    0.40
     fella
    0.40
    Activations Density 0.128%

    No Known Activations