© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3716
    Prev
    Next
    INDEX
    Explanations

    words related to research processes, especially those involving experts, teams, and analysis

    oai_token-act-pair · gemini-2.0-flash

    technical texts

    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
    IntoConstraints
    -0.74
    niająca
    -0.58
     msglen
    -0.57
    GraphicsUnit
    -0.56
    WithMany
    -0.56
    ۇ
    -0.55
    kháu
    -0.53
    dropna
    -0.53
     varandra
    -0.53
    Tikang
    -0.53
    POSITIVE LOGITS
     fine
    0.69
    Fine
    0.58
     flesh
    0.58
    fine
    0.56
     Fine
    0.56
    WebElementEntity
    0.55
    دانشنامهٔ
    0.54
     crystal
    0.53
    发表于
    0.49
     FINE
    0.49
    Activations Density 3.403%

    No Known Activations