© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 6537
    Prev
    Next
    INDEX
    Explanations

    legal jargon from court documents and legal arguments.

    oai_token-act-pair · gemini-2.0-flash

    legal/formal writing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     utafitiHapana
    -0.74
     tombé
    -0.59
     fieldNum
    -0.56
    ImageContext
    -0.56
    FunctionFlags
    -0.54
    IVEREF
    -0.52
    ंदीखरीदारी
    -0.52
    fjspx
    -0.50
    zur
    -0.50
    TableBody
    -0.49
    POSITIVE LOGITS
     CreateTagHelper
    0.79
    toMatchSnapshot
    0.54
    enumi
    0.54
    NegativeButton
    0.53
     estimés
    0.53
    Примітки
    0.51
    ESTRA
    0.50
    存于互联网档案馆
    0.50
    千里
    0.49
    مصادر
    0.47
    Activations Density 14.292%

    No Known Activations