© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11460
    Prev
    Next
    INDEX
    Explanations

    terms related to physics experiments and measurements

    oai_token-act-pair · gemini-2.0-flash

    diverse terms related to research and documentation

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

    dark matter/neutrino research

    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
    PMailer
    -0.56
     Hout
    -0.49
    一提
    -0.48
     Roskov
    -0.48
     Parole
    -0.48
    sky
    -0.47
     Yoko
    -0.46
     Infórmanos
    -0.46
     gluta
    -0.46
    avad
    -0.46
    POSITIVE LOGITS
     EconPapers
    0.68
     dignité
    0.64
    Izvori
    0.60
    verwijspagina
    0.58
     stanovnika
    0.56
    expandindo
    0.56
    CppMethod
    0.56
    ligible
    0.56
    verhältnisse
    0.56
    bootstrapcdn
    0.54
    Activations Density 1.479%

    No Known Activations