© 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. 2838
    Prev
    Next
    INDEX
    Explanations

    words related to locations and dates

    oai_token-act-pair · gemini-2.0-flash

    programming-related terms

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

    Boston

    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
    Fcn
    -0.64
    dialect
    -0.62
     Wiktionnaire
    -0.55
    lccn
    -0.54
    SharedCtor
    -0.52
     EconPapers
    -0.52
    таратура
    -0.52
     Normdatei
    -0.52
    ArgsConstructor
    -0.51
     doInBackground
    -0.51
    POSITIVE LOGITS
    stdc
    0.56
    UrlResolution
    0.49
    __()
    0.47
    rew
    0.44
    assertTrue
    0.43
    дели
    0.43
    новь
    0.43
     Quig
    0.42
    kannya
    0.42
     raw
    0.42
    Activations Density 4.525%

    No Known Activations