© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5228
    Prev
    Next
    INDEX
    Explanations

    the capitalized word "Cap".

    oai_token-act-pair · gemini-2.0-flash

    cap

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    MigrationBuilder
    -0.74
    
    -0.71
    BeginInit
    -0.57
    بات
    -0.54
    responseText
    -0.53
     nahilalakip
    -0.52
    nosaurus
    -0.51
    asanjo
    -0.50
    ActionCreators
    -0.50
    afterEach
    -0.50
    POSITIVE LOGITS
    Хьажоргаш
    0.59
    Попис
    0.46
    rophe
    0.45
    fruit
    0.45
    Comté
    0.44
    WriteAttribute
    0.44
     Reliance
    0.43
    nachron
    0.43
    copg
    0.43
    ніципа
    0.43
    Activations Density 0.772%

    No Known Activations