© 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. 5758
    Prev
    Next
    INDEX
    Explanations

    the beginnings of sentences and musical artists along with the word "vibes."

    oai_token-act-pair · gemini-2.0-flash

    Random texts

    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
     colorear
    -0.48
    mazione
    -0.45
    bereitung
    -0.45
    quillo
    -0.44
    請繼續往下閱讀
    -0.44
     funcionales
    -0.43
    ąd
    -0.43
     juos
    -0.43
     kabát
    -0.43
     picioare
    -0.42
    POSITIVE LOGITS
    SequentialGroup
    0.79
    LookAnd
    0.77
    tagHelper
    0.73
    IndentedString
    0.71
    ]")]
    0.69
    )))));
    0.68
    Personendaten
    0.68
     RemoteException
    0.66
    ollection
    0.66
    protoc
    0.65
    Activations Density 17.003%

    No Known Activations