© 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. 3301
    Prev
    Next
    INDEX
    Explanations

    language used in legal documents regarding judgment and prejudice

    oai_token-act-pair · gemini-2.0-flash

    legal documentation

    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
     Sec
    -0.49
     Smyth
    -0.47
     Son
    -0.46
    VELOP
    -0.44
     Bros
    -0.43
    PONSE
    -0.42
     Bro
    -0.42
    iforn
    -0.41
     Frame
    -0.41
    NOSIS
    -0.41
    POSITIVE LOGITS
    DeleteBehavior
    0.77
    Personensuche
    0.73
    rungsseite
    0.73
     &___
    0.70
    Autoritní
    0.68
    AndEndTag
    0.68
     Shakspeare
    0.68
     >=",
    0.68
     autorytatywna
    0.67
    таратура
    0.67
    Activations Density 5.072%

    No Known Activations