© 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. 15902
    Prev
    Next
    INDEX
    Explanations

    angry, antagonistic ranting

    oai_token-act-pair · gemini-2.0-flash

    online arguments/controversy

    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
     يتيمه
    -0.60
     RIPRODUZIONE
    -0.59
     Leute
    -0.54
     guys
    -0.54
     föruts
    -0.50
    WriteBarrier
    -0.50
     godk
    -0.50
    guien
    -0.50
     médicas
    -0.49
    RetentionPolicy
    -0.49
    POSITIVE LOGITS
    OGND
    0.78
    MessageTagHelper
    0.77
    Chham
    0.71
    ScopeManager
    0.68
     broad
    0.67
     prick
    0.66
    はじめに
    0.66
     punk
    0.65
     b
    0.65
    Geografía
    0.63
    Activations Density 1.149%

    No Known Activations