© 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
    2. Gemma-2-2B
    3. 8-GEMMASCOPE-TRANSCODER-16K
    4. 1328
    Prev
    Next
    INDEX
    Explanations

    language related to legal or policy decisions about equal rights and treatment

    oai_token-act-pair · gemini-2.0-flash

    treatment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    TypedDataSet
    -0.71
     betweenstory
    -0.68
    $_['
    -0.57
    
    -0.56
     صوتيه
    -0.56
     uſe
    -0.53
    afficheront
    -0.53
    moduleId
    -0.53
    astify
    -0.53
    Décès
    -0.52
    POSITIVE LOGITS
    kuuta
    0.53
    LayoutStyle
    0.52
     förm
    0.51
     amarillas
    0.49
     kautta
    0.47
    hoebe
    0.47
     censiti
    0.46
     doigt
    0.45
    UnknownFieldSet
    0.45
    contentLoaded
    0.44
    Activations Density 1.821%

    No Known Activations