© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 3713
    Prev
    Next
    INDEX
    Explanations

    math and coding syntax often found in research articles

    oai_token-act-pair · gemini-2.0-flash

    proofs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     IFTT
    -0.90
    الإنجليزية
    -0.90
    ValueStyle
    -0.89
     صوتيه
    -0.85
    fjspx
    -0.82
     ModelExpression
    -0.82
     &___
    -0.77
     فريبيس
    -0.76
    StoryboardSegue
    -0.75
     dAtA
    -0.72
    POSITIVE LOGITS
    ждый
    0.52
     cleared
    0.42
    maz
    0.41
    ีย์
    0.40
     male
    0.40
    ostante
    0.40
    Un
    0.39
    ']=='
    0.39
    会上
    0.39
    دام
    0.37
    Activations Density 9.237%

    No Known Activations