© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 8015
    Prev
    Next
    INDEX
    Explanations

    references to numerical values and time periods, often including the words "one", "twenty, "days", and "years".

    oai_token-act-pair · gemini-2.0-flash

    Time or ages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     twenty
    -2.33
     thirty
    -2.25
     forty
    -2.23
     fifty
    -2.22
     seventy
    -2.16
     sixty
    -2.16
     eighty
    -2.11
    twenty
    -2.06
     fifteen
    -2.06
     eighteen
    -2.05
    POSITIVE LOGITS
     autorytatywna
    0.57
     виправивши
    0.56
    kunft
    0.56
    ionales
    0.53
     MenuView
    0.52
     Meksiku
    0.51
    droje
    0.51
     препратки
    0.50
    Джерела
    0.49
     marquées
    0.49
    Activations Density 3.993%

    No Known Activations