© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12103
    Prev
    Next
    INDEX
    Explanations

    the pronouns "this", "these", "one", and sometimes "it", and less frequently "we" and "I"

    oai_token-act-pair · gemini-2.0-flash

    this/these

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     Réponses
    -0.60
    enterOuterAlt
    -0.59
    styleUrls
    -0.59
    putchar
    -0.55
    Subviews
    -0.54
    titut
    -0.54
    /***/
    -0.53
    Hozzáférés
    -0.53
    DropTable
    -0.53
    getValueAt
    -0.53
    POSITIVE LOGITS
     typelib
    0.61
    :✨
    0.59
    AutoField
    0.56
     siyang
    0.56
    Попис
    0.55
    MigrationBuilder
    0.52
    affaire
    0.51
    存于互联网档案馆
    0.51
     papiers
    0.50
     Factbook
    0.49
    Activations Density 0.425%

    No Known Activations