© 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. 12841
    Prev
    Next
    INDEX
    Explanations

    teams, particularly sports teams, and their competition

    oai_token-act-pair · gemini-2.0-flash

    negotiations and agreements

    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
    GOTREF
    -0.54
    oredCriteria
    -0.48
    הערות
    -0.47
    Personendaten
    -0.46
    findpost
    -0.46
    askar
    -0.43
    árbol
    -0.42
     ángeles
    -0.42
     riferimento
    -0.42
    mention
    -0.41
    POSITIVE LOGITS
    !*\
    0.81
     ISNI
    0.69
     Agree
    0.68
    mybatisplus
    0.65
    tanleria
    0.64
    schild
    0.64
     squared
    0.63
    entary
    0.62
     agree
    0.61
    sizeCache
    0.61
    Activations Density 1.865%

    No Known Activations