© 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. 13323
    Prev
    Next
    INDEX
    Explanations

    C# code snippets working with LINQ queries

    oai_token-act-pair · gemini-2.0-flash

    brackets and punctuation

    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
     configureStore
    -0.67
    arriver
    -0.63
     Roskov
    -0.62
     VPN
    -0.62
    gebras
    -0.60
    adeloupe
    -0.59
    ValueGenerated
    -0.59
     Wikimedijinoj
    -0.59
     @"/
    -0.58
    gebob
    -0.58
    POSITIVE LOGITS
    లాలు
    0.46
    laş
    0.43
     lineal
    0.43
     vivimos
    0.40
     stabilis
    0.40
    nambuco
    0.40
     parchment
    0.40
     clon
    0.39
    באנגלית
    0.38
    sample
    0.38
    Activations Density 0.326%

    No Known Activations