© 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. 5514
    Prev
    Next
    INDEX
    Explanations

    question answer pairs and lists within documents

    oai_token-act-pair · gemini-2.0-flash

    questions

    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
    UserScript
    -0.78
    RetentionPolicy
    -0.75
    contentLoaded
    -0.74
     Inscrivez
    -0.67
     ftate
    -0.66
     niyang
    -0.66
     Gallimard
    -0.65
     Silurian
    -0.65
    TypedDataSet
    -0.64
     neceff
    -0.62
    POSITIVE LOGITS
     May
    0.76
    May
    0.75
     Am
    0.73
     may
    0.68
    Am
    0.67
    may
    0.66
     am
    0.65
     Do
    0.56
     kasarigan
    0.54
    Do
    0.54
    Activations Density 8.887%

    No Known Activations