© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 8051
    Prev
    Next
    INDEX
    Explanations

    the word "informed."

    oai_token-act-pair · gemini-2.0-flash

    informed

    np_max-act · 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
    stanza
    -0.59
    iting
    -0.55
    .)}
    -0.54
     great
    -0.54
     team
    -0.53
    ynes
    -0.52
    ')));
    -0.52
    recie
    -0.52
     */;
    -0.51
     Qué
    -0.50
    POSITIVE LOGITS
    <bos>
    1.49
    AutoScale
    0.62
    AddTagHelper
    0.60
    To
    0.59
    
    0.57
     Савезне
    0.56
    .
    0.56
     mierda
    0.54
     infierno
    0.54
    MigrationBuilder
    0.54
    Activations Density 0.602%

    No Known Activations