© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 11369
    Prev
    Next
    INDEX
    Explanations

    Java stack traces or other error messages

    oai_token-act-pair · gemini-2.0-flash

    e

    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
    localctx
    -0.91
     Савезне
    -0.87
    GEBURTS
    -0.85
     ExecuteAsync
    -0.84
     للمعارف
    -0.82
    awtextra
    -0.79
     Мексичка
    -0.75
    ">//
    -0.75
    ')['
    -0.75
    });*/
    -0.74
    POSITIVE LOGITS
    ละเอียด
    0.40
    kå
    0.40
     peças
    0.38
    Loki
    0.38
    wilson
    0.38
    vetica
    0.38
     grises
    0.37
    russian
    0.36
    LBL
    0.36
    過來
    0.36
    Activations Density 5.436%

    No Known Activations