© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 11001
    Prev
    Next
    INDEX
    Explanations

    text describing a scientific experiment

    oai_token-act-pair · gemini-2.0-flash

    microscopy analysis

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    TagMode
    -0.91
    CodeAttribute
    -0.81
    IUrlHelper
    -0.78
    MLLoader
    -0.74
     onOptions
    -0.72
    Portail
    -0.71
    StoreMessageInfo
    -0.69
    saraba
    -0.68
     سكانية
    -0.66
    WriteBarrier
    -0.65
    POSITIVE LOGITS
    elden
    0.46
    '][]
    0.44
    кзак
    0.43
    BaseModel
    0.43
    GAIN
    0.42
     Grand
    0.41
    برى
    0.41
    crowned
    0.41
    ERY
    0.40
     Hinter
    0.40
    Activations Density 2.016%

    No Known Activations