© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3925
    Prev
    Next
    INDEX
    Explanations

    calculations involving numbers, parentheses, or multiplication

    oai_token-act-pair · gemini-2.0-flash

    programming-related keywords or functions

    np_token-act-pair-logits · gpt-4o-mini

    Calculations/Code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/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.21.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
     CreateTagHelper
    -0.61
    LElement
    -0.58
    jspx
    -0.51
     Erasmus
    -0.50
    harusnya
    -0.49
    %")
    -0.49
    tidaknya
    -0.48
    utilisons
    -0.48
    hibli
    -0.48
    bootstrapcdn
    -0.47
    POSITIVE LOGITS
    Datuak
    0.69
    AlterField
    0.63
    HasIndex
    0.58
    providedIn
    0.55
     bezeichneter
    0.52
     createContext
    0.51
     tartalomajánló
    0.51
     HasFactory
    0.50
    ieteur
    0.50
    بوابة
    0.49
    Activations Density 0.876%

    No Known Activations