© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 2256
    Prev
    Next
    INDEX
    Explanations

    numbers or code.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    COUVER
    -0.50
    APORE
    -0.48
    apore
    -0.46
    glTexCoord
    -0.44
    haviour
    -0.42
    prehensive
    -0.42
    adura
    -0.41
    tona
    -0.40
    URN
    -0.38
    ellery
    -0.37
    POSITIVE LOGITS
    SharedDtor
    0.74
    8
    0.72
    7
    0.70
    9
    0.69
    msgTypes
    0.69
    2
    0.66
    انيف
    0.65
     ComVisible
    0.63
     pinulongan
    0.62
     Infórmanos
    0.61
    Activations Density 33.046%

    No Known Activations