© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 5367
    Prev
    Next
    INDEX
    Explanations

    mentions of numerical quantities

    oai_token-act-pair · gemini-2.0-flash

    Numbers under twenty

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    featureID
    -1.04
    Geplaatst
    -0.94
     AttributeSet
    -0.92
     فريبيس
    -0.84
     nahilalakip
    -0.83
     bezeichneter
    -0.83
     ProtoMessage
    -0.79
     препратки
    -0.78
    abestanden
    -0.78
     onOptions
    -0.78
    POSITIVE LOGITS
     ten
    0.40
     about
    0.40
     twelve
    0.40
     eleven
    0.39
     thirteen
    0.39
     nine
    0.39
     Româ
    0.37
     fifteen
    0.37
    eight
    0.36
     eight
    0.36
    Activations Density 7.199%

    No Known Activations