© 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. 7890
    Prev
    Next
    INDEX
    Explanations

    strings of numbers, often dates, times, or version numbers, sometimes in the context of scientific data

    oai_token-act-pair · gemini-2.0-flash

    complex or compound terms

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

    0

    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
    GEBURTSDATUM
    -0.75
    انجليز
    -0.63
     getItemId
    -0.58
    hoeddwyd
    -0.56
     autorytatywna
    -0.56
    лтемелер
    -0.56
    FieldNumber
    -0.53
    மே
    -0.53
    protoc
    -0.53
    FormTagHelper
    -0.52
    POSITIVE LOGITS
    TagMode
    0.59
    Спољашње
    0.50
     compromises
    0.49
     EconPapers
    0.48
     confronti
    0.47
    illée
    0.46
    Viitteet
    0.46
     AudioClip
    0.46
    مصادر
    0.46
    illées
    0.46
    Activations Density 1.317%

    No Known Activations