© 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. 5935
    Prev
    Next
    INDEX
    Explanations

    the capital letter L followed by a period, or a single capital letter followed by a period.

    oai_token-act-pair · 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
    parsedMessage
    -0.90
    rawDesc
    -0.89
    RegistryLite
    -0.86
    Datuak
    -0.85
     wireType
    -0.85
     الحره
    -0.82
    CodedInputStream
    -0.77
    IsMutable
    -0.76
    новништво
    -0.75
    StoryboardSegue
    -0.71
    POSITIVE LOGITS
    A
    0.79
    C
    0.75
    P
    0.73
    R
    0.73
    V
    0.70
    M
    0.69
    E
    0.67
    U
    0.65
    L
    0.65
    I
    0.65
    Activations Density 3.572%

    No Known Activations