© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 7350
    Prev
    Next
    INDEX
    Explanations

    nouns that are either technical, physical objects, or ingredients/elements of some kind.

    oai_token-act-pair · gemini-2.0-flash

    "for" in other languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.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
    ✭✭
    -0.57
    Попис
    -0.56
    pora
    -0.56
    UnknownFieldSet
    -0.49
    Stand
    -0.49
     Masih
    -0.49
    ValueGeneration
    -0.49
    pegno
    -0.49
    duino
    -0.49
    assertIs
    -0.49
    POSITIVE LOGITS
     for
    0.82
     untuk
    0.74
     для
    0.71
     برای
    0.57
     suitable
    0.56
    для
    0.54
     fürs
    0.54
    สำหรับ
    0.54
    用于
    0.54
     dla
    0.53
    Activations Density 1.667%

    No Known Activations