© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 2988
    Prev
    Next
    INDEX
    Explanations

    the word "adult"

    oai_token-act-pair · gemini-2.0-flash

    adult

    np_max-act · gemini-2.0-flash

    adult

    np_max-act-logits · gpt-5-mini
    Triggered 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
    Negative Logits
    ]));
    -0.98
     ་་
    -0.91
     ―――――
    -0.90
     resourceCulture
    -0.89
    awtextra
    -0.85
    }^{+\
    -0.78
     ſch
    -0.75
     Dece
    -0.74
    theless
    -0.74
     {},
    -0.74
    POSITIVE LOGITS
    .
    0.83
     conna
    0.61
     noël
    0.59
    visející
    0.58
     that
    0.58
     maestra
    0.56
     aveug
    0.54
     I
    0.53
    dotta
    0.52
     citta
    0.52
    Activations Density 1.289%

    No Known Activations