© 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. 4536
    Prev
    Next
    INDEX
    Explanations

    pieces of computer code

    oai_token-act-pair · gemini-2.0-flash

    ellipses

    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
    .
    -0.85
     vermelha
    -0.77
     brancas
    -0.77
     vectorielle
    -0.76
     judiciaire
    -0.74
     vermelhas
    -0.73
     dourada
    -0.73
     sanitaires
    -0.71
     humaine
    -0.71
     femininos
    -0.71
    POSITIVE LOGITS
    <bos>
    0.91
     كومونز
    0.83
     Савезне
    0.76
    }}_
    0.74
    WebVitals
    0.71
    ThemeOverlay
    0.70
    ]_
    0.69
    OGND
    0.69
     []);
    0.68
     Emb
    0.63
    Activations Density 0.381%

    No Known Activations