© 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. 5360
    Prev
    Next
    INDEX
    Explanations

    words describing a graphical user interface, especially on phones

    oai_token-act-pair · gemini-2.0-flash

    user interfaces

    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
     urbanas
    -0.53
     devriez
    -0.53
     pregunto
    -0.53
    loroethene
    -0.52
    AddField
    -0.50
     dietro
    -0.49
     invokingState
    -0.49
    AlterField
    -0.48
    protoimpl
    -0.47
    nsito
    -0.47
    POSITIVE LOGITS
    MLLoader
    0.55
    bollah
    0.55
     distanciation
    0.54
     IDL
    0.53
    WriteAttribute
    0.53
    zość
    0.52
     BorderRadius
    0.50
     Orto
    0.50
    LookAnd
    0.49
    contentLoaded
    0.49
    Activations Density 15.292%

    No Known Activations