© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 3572
    Prev
    Next
    INDEX
    Explanations

    pronouns and words directly related to people, or referencing those people

    oai_token-act-pair · gemini-2.0-flash

    dialogues and conversations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    PreferredItem
    -0.66
    :+:
    -0.60
     responding
    -0.59
     responden
    -0.58
     rispondere
    -0.58
     '\\;'
    -0.57
    setViewportView
    -0.57
     antworten
    -0.57
    respond
    -0.57
    Билгалдахарш
    -0.56
    POSITIVE LOGITS
    WebElementEntity
    0.57
    ثيق
    0.56
    AndEndTag
    0.56
    MessageTagHelper
    0.53
     CURIAM
    0.52
     Giovan
    0.52
    AddTagHelper
    0.50
    ỡng
    0.50
    ymce
    0.49
     myſelf
    0.49
    Activations Density 6.347%

    No Known Activations