© 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. 2570
    Prev
    Next
    INDEX
    Explanations

    a mix of computer code, medical terminology and Korean names

    oai_token-act-pair · gemini-2.0-flash

    Abbreviations, names, and code

    np_max-act · gemini-2.0-flash

    j

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
    forhold
    -0.54
     slutt
    -0.53
     osal
    -0.52
     fhort
    -0.50
     Barrera
    -0.48
     våre
    -0.48
     mohli
    -0.46
     vores
    -0.46
    ArrowToggle
    -0.46
     virš
    -0.45
    POSITIVE LOGITS
    "]
    0.78
     BoxDecoration
    0.75
    ']))
    0.73
    ."]
    0.73
    }])
    0.73
    principalTable
    0.73
     通販
    0.72
    UnknownFields
    0.69
    webElement
    0.68
    ")]
    0.68
    Activations Density 2.346%

    No Known Activations