© 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. 14182
    Prev
    Next
    INDEX
    Explanations

    code snippets in Portuguese that contain compilation or memory errors

    oai_token-act-pair · gemini-2.0-flash

    code snippets

    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
    
    -0.64
    mogat
    -0.61
     contextLoads
    -0.60
     Roskov
    -0.59
     <<<<<<<<<<<<<<
    -0.59
     invokingState
    -0.57
    ojos
    -0.57
    Izvori
    -0.56
    RTHOOK
    -0.56
     ModelExpression
    -0.55
    POSITIVE LOGITS
     Mor
    0.56
    Mor
    0.54
    IntoConstraints
    0.48
    GeneratedValue
    0.48
    ps
    0.47
     tempo
    0.47
    ]='\
    0.46
    diano
    0.45
     Tempo
    0.45
    Frequent
    0.45
    Activations Density 0.528%

    No Known Activations