© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 8520
    Prev
    Next
    INDEX
    Explanations

    descriptions of damage to products

    oai_token-act-pair · gemini-2.0-flash

    Technical problems and defects

    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
     pinulongan
    -0.66
    ühungen
    -0.50
     ↓,
    -0.48
     Psy
    -0.46
     accomod
    -0.43
     onCreateView
    -0.43
     snippetHide
    -0.42
    isContained
    -0.41
     gratu
    -0.41
     Spot
    -0.41
    POSITIVE LOGITS
    WebControls
    0.71
    MessageOf
    0.68
    bufio
    0.62
     كومونز
    0.62
    ContentAsync
    0.61
    BoxShadow
    0.59
    Tikang
    0.58
    WriteAttribute
    0.58
    GraphicsUnit
    0.57
    toHaveBeenCalled
    0.56
    Activations Density 3.047%

    No Known Activations