© 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. 5007
    Prev
    Next
    INDEX
    Explanations

    words related to mistakes

    oai_token-act-pair · gemini-2.0-flash

    missing something

    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
    anywhere
    -0.68
    everywhere
    -0.68
    somewhere
    -0.65
     Elsewhere
    -0.63
     Other
    -0.63
    OTHER
    -0.60
     Anywhere
    -0.60
    Nothing
    -0.60
    Other
    -0.58
     Otros
    -0.58
    POSITIVE LOGITS
     sum
    0.77
     resourceCulture
    0.71
    titleMargin
    0.69
     som
    0.66
    Som
    0.66
     sump
    0.62
     somme
    0.61
     sm
    0.60
     soma
    0.60
     ivelany
    0.59
    Activations Density 0.936%

    No Known Activations