© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 3749
    Prev
    Next
    INDEX
    Explanations

    conversational pronouns and related words like "you", "we", "I", "have", and "could".

    oai_token-act-pair · gemini-2.0-flash

    "having" in multiple 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_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     réessayer
    -0.64
     pinulongan
    -0.60
     jsPsych
    -0.59
    OfBirth
    -0.59
    oyama
    -0.54
    labelledby
    -0.53
    opensource
    -0.52
    AddHtmlAttribute
    -0.51
    zeba
    -0.51
    xious
    -0.51
    POSITIVE LOGITS
     having
    1.25
    having
    1.14
    Having
    1.09
     Having
    1.06
    有
    1.00
     có
    0.98
     memiliki
    0.93
     HAVING
    0.92
     avere
    0.91
     had
    0.83
    Activations Density 2.662%

    No Known Activations