© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 4446
    Prev
    Next
    INDEX
    Explanations

    code snippets, and particularly code with underscores, and the word "map"

    oai_token-act-pair · gemini-2.0-flash

    programming code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    adaptiveStyles
    -0.89
    sizeCache
    -0.78
    msgTypes
    -0.75
     hObject
    -0.74
    UIControlState
    -0.74
     defaultstate
    -0.66
     <<<<<<<<<<<<<<
    -0.66
     censi
    -0.65
     QtCore
    -0.65
    RTDA
    -0.63
    POSITIVE LOGITS
     flag
    0.45
    Recall
    0.43
    ]$}
    0.42
    檚
    0.42
     Flag
    0.41
    iestety
    0.40
    RAINE
    0.40
     juntas
    0.40
    旗
    0.40
    ')}
    0.40
    Activations Density 2.957%

    No Known Activations