© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10332
    Prev
    Next
    INDEX
    Explanations

    technical results from scientific studies

    oai_token-act-pair · gemini-2.0-flash

    Scientific measurements/comparisons

    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
     astore
    -0.55
    vyš
    -0.50
    gitte
    -0.49
     angem
    -0.47
    cipline
    -0.44
     kiti
    -0.44
    τία
    -0.44
     Hach
    -0.44
    diak
    -0.43
     liev
    -0.43
    POSITIVE LOGITS
    rrggbb
    0.72
    <?
    0.62
    EndProject
    0.61
    DebuggerNonUser
    0.59
    Revenir
    0.58
     <<<<<<<<<<<<<<
    0.58
    cshtml
    0.57
    DoubleQuotes
    0.57
    MouseAdapter
    0.57
    ≦)
    0.56
    Activations Density 19.574%

    No Known Activations