© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 4846
    Prev
    Next
    INDEX
    Explanations

    digits with a high weighting for 6

    oai_token-act-pair · gemini-2.0-flash

    1

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    "]));
    -0.89
    ;*/
    -0.79
    "])
    -0.77
    IUrlHelper
    -0.77
    '])->
    -0.77
    "])
    -0.72
    '])
    -0.72
    ']));
    -0.71
    '],
    -0.71
    "]))
    -0.71
    POSITIVE LOGITS
    bhan
    0.54
     EconPapers
    0.51
    AndroidJUnit
    0.51
    SequentialGroup
    0.50
    ніципалі
    0.50
    InstanceState
    0.50
    ToRefresh
    0.49
    Quarter
    0.48
    inander
    0.48
    دانشنامهٔ
    0.48
    Activations Density 0.173%

    No Known Activations