© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 2997
    Prev
    Next
    INDEX
    Explanations

    legal and medical language related to stopping something, especially abortion or abduction

    oai_token-act-pair · gemini-2.0-flash

    ab

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     ab
    -2.47
     Ab
    -2.42
    Ab
    -2.33
    ab
    -1.98
     AB
    -1.91
    AB
    -1.71
     Аб
    -1.39
     abf
    -1.38
     Abi
    -1.37
     ABR
    -1.35
    POSITIVE LOGITS
    bno
    0.39
     ngoài
    0.38
    قي
    0.38
     копи
    0.38
    feira
    0.36
    lanmış
    0.36
    emia
    0.35
     Copy
    0.35
    gleich
    0.35
    geschäft
    0.35
    Activations Density 2.413%

    No Known Activations