© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 14822
    Prev
    Next
    INDEX
    Explanations

    auxiliary verbs (is, has, had, are) followed by past participles or adjectives and/or nouns related to pregnancy.

    oai_token-act-pair · gemini-2.0-flash

    Occurrence and existence

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     дописавши
    -0.92
     استنادى
    -0.60
    脚注の使い方
    -0.59
    potranspiration
    -0.59
    HasForeignKey
    -0.59
     sauvages
    -0.55
    مصادر
    -0.55
    ypep
    -0.54
    prnewswire
    -0.54
     acompañado
    -0.54
    POSITIVE LOGITS
     or
    0.69
     یا
    0.56
    DebuggerNonUser
    0.56
    或
    0.56
    OrUpdate
    0.54
     يا
    0.54
     или
    0.54
     hoặc
    0.53
     ή
    0.52
     oder
    0.52
    Activations Density 0.411%

    No Known Activations