© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 15082
    Prev
    Next
    INDEX
    Explanations

    words related to political, creative, and natural upheavals.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    ↵↵
    -0.77
    <bos>
    -0.76
    ↵
    -0.65
    a
    -0.51
    2
    -0.50
    1
    -0.49
    '
    -0.47
    4
    -0.46
     and
    -0.44
    3
    -0.44
    POSITIVE LOGITS
    KommentareTeilen
    1.29
    tvguidetime
    1.15
    AnchorStyles
    1.04
    findpost
    1.04
    Gambas
    0.98
    脚注の使い方
    0.96
    MENAFN
    0.96
    AddTagHelper
    0.95
     оригіналу
    0.95
     cherchés
    0.94
    Activations Density 2.060%

    No Known Activations