© 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. 1641
    Prev
    Next
    INDEX
    Explanations

    words related to science, law, electronics, and general academia

    oai_token-act-pair · gemini-2.0-flash

    academic/technical texts

    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
    WriteBarrier
    -0.73
    tvguidetime
    -0.69
    曖昧さ回避
    -0.63
    intenant
    -0.63
     الحره
    -0.62
    ]),
    -0.59
    JsonHelper
    -0.57
    detectChanges
    -0.56
    السلام
    -0.56
    PyExc
    -0.56
    POSITIVE LOGITS
    ArgsConstructor
    0.51
     ex
    0.48
     lo
    0.48
     x
    0.47
     通販
    0.47
    ex
    0.44
    ukone
    0.44
     tri
    0.43
    ícil
    0.43
    ługi
    0.42
    Activations Density 2.605%

    No Known Activations