© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 14441
    Prev
    Next
    INDEX
    Explanations

    words related to going beyond normal expected actions or features

    oai_token-act-pair · gemini-2.0-flash

    terms indicating additional components or layers

    np_token-act-pair-logits · gpt-4o-mini

    extra

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     CreateTagHelper
    -0.81
    WebVitals
    -0.78
     BoxFit
    -0.74
    adpleegd
    -0.69
     esternos
    -0.66
     stället
    -0.66
    Geplaatst
    -0.65
    EDEFAULT
    -0.65
    脚注の使い方
    -0.64
     unknownFields
    -0.64
    POSITIVE LOGITS
    getWriter
    0.57
     layers
    0.54
     layer
    0.50
     fuzz
    0.50
    횟
    0.50
    xor
    0.50
     sin
    0.50
     Layers
    0.49
     fees
    0.49
     sauce
    0.47
    Activations Density 3.992%

    No Known Activations