© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 4759
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and words describing demographic groups, devices, or medical terminology

    oai_token-act-pair · gemini-2.0-flash

    -

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    -
    -0.54
     fraî
    -0.44
     perdita
    -0.41
     alami
    -0.41
     élect
    -0.39
    aro
    -0.39
    mp
    -0.38
     rojas
    -0.37
     promessa
    -0.37
     tölt
    -0.36
    POSITIVE LOGITS
     '\\;'
    1.31
     تضيفلها
    1.31
    oredCriteria
    1.22
    +#+#
    1.15
    цездатний
    1.15
     autorytatywna
    1.14
    AutoScaleMode
    1.13
    tagHelperRunner
    1.12
    UnsafeEnabled
    1.10
    CloseOperation
    1.09
    Activations Density 3.085%

    No Known Activations