© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4288
    Prev
    Next
    INDEX
    Explanations

    text discussing medical research and treatment

    oai_token-act-pair · gemini-2.0-flash

    technical terminology or specialized terms

    np_token-act-pair-logits · gpt-4o-mini

    Medical texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     nakalista
    -0.77
    Datuak
    -0.69
     AspNetCore
    -0.67
     saites
    -0.66
    ]:
    -0.63
    }]);
    -0.62
    DockStyle
    -0.60
    Personendaten
    -0.60
    Pautan
    -0.60
    '],
    -0.60
    POSITIVE LOGITS
     صوتيه
    0.69
     esquema
    0.57
     Cervantes
    0.49
    牵
    0.45
     esquem
    0.45
    циональный
    0.42
    icide
    0.42
     voici
    0.42
    stateParams
    0.42
    Schemes
    0.42
    Activations Density 3.050%

    No Known Activations