© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 14787
    Prev
    Next
    INDEX
    Explanations

    words related to physical space, especially movement, location, and body parts.

    oai_token-act-pair · gemini-2.0-flash

    hanging

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    )");
    -0.63
    érience
    -0.57
     userSchema
    -0.57
     ARXIV
    -0.54
    ihnachten
    -0.53
     MOA
    -0.53
     Def
    -0.52
     "];
    -0.52
     LoginComponent
    -0.52
    "));
    -0.51
    POSITIVE LOGITS
    Personendaten
    0.68
    rungsseite
    0.57
    ArgsConstructor
    0.55
    Datuak
    0.52
    abestanden
    0.50
     frisk
    0.49
    Aktualisiert
    0.49
    isContained
    0.48
    Obrázky
    0.48
    
    0.45
    Activations Density 8.122%

    No Known Activations