© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4696
    Prev
    Next
    INDEX
    Explanations

    text that is very weird, possibly a hallucination as it mixes programming debugging information, medical conditions, and economics

    oai_token-act-pair · gemini-2.0-flash

    technical and foreign content

    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
    able
    -0.87
    oader
    -0.74
    auff
    -0.73
    WithIOException
    -0.68
    ach
    -0.66
    aufs
    -0.65
    ables
    -0.65
    ado
    -0.63
    ably
    -0.63
    runk
    -0.63
    POSITIVE LOGITS
    rizona
    0.48
     originais
    0.44
    CAPTION
    0.44
    **
    0.41
     plufieurs
    0.40
     engraçadas
    0.40
     Еще
    0.39
     Архів
    0.39
    tığı
    0.39
    тером
    0.38
    Activations Density 0.580%

    No Known Activations