© 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. 8008
    Prev
    Next
    INDEX
    Explanations

    mentions of a female subject

    oai_token-act-pair · gemini-2.0-flash

    she

    np_max-act · gemini-2.0-flash

    ▁she

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
    AddTagHelper
    -1.27
    tagHelperRunner
    -1.23
     NSCoder
    -1.20
    DoubleQuotes
    -1.20
    migrationBuilder
    -1.18
    enderror
    -1.17
     utafitiHapana
    -1.13
    IntoConstraints
    -1.11
    UnusedPrivate
    -1.09
    AutoScaleMode
    -1.02
    POSITIVE LOGITS
    <bos>
    1.15
    ↵↵
    1.06
    '
    1.04
     and
    0.89
    ↵
    0.87
     
    0.82
    ’
    0.77
    ,
    0.77
    <eos>
    0.71
    .
    0.71
    Activations Density 8.697%

    No Known Activations