© 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. 11605
    Prev
    Next
    INDEX
    Explanations

    music bands which include the word "The"

    oai_token-act-pair · gemini-2.0-flash

    Song/band names

    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
     purpoſe
    -0.77
     houſe
    -0.71
     regency
    -0.68
     pinulongan
    -0.67
     يتيمه
    -0.66
     Monfieur
    -0.66
     itſelf
    -0.66
     poffe
    -0.65
     myſelf
    -0.65
    ſelf
    -0.64
    POSITIVE LOGITS
    ]")]
    0.50
     Ram
    0.48
    requireNonNull
    0.47
     Human
    0.45
     Sto
    0.44
    createServer
    0.44
    stdc
    0.44
    kesha
    0.43
     KIN
    0.43
    mme
    0.43
    Activations Density 0.758%

    No Known Activations