© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 7325
    Prev
    Next
    INDEX
    Explanations

    legal jargon including Title and Section symbols, numbers, Courts, Acts, prison, etc. in laws, cases, statutes, codes and opinions.

    oai_token-act-pair · gemini-2.0-flash

    One or zero

    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
    Референце
    -0.72
    [];
    -0.56
     nargin
    -0.56
    UserRepository
    -0.55
     Efq
    -0.54
     Monfieur
    -0.54
     Holo
    -0.54
    PDOException
    -0.53
    Erreferentziak
    -0.52
     背影
    -0.51
    POSITIVE LOGITS
    landaise
    0.57
    béco
    0.52
    afficheront
    0.52
     estekak
    0.49
     iconLine
    0.48
    ViewFeatures
    0.47
    ftagPool
    0.47
    cbf
    0.44
     незавершена
    0.44
    XMLSchema
    0.44
    Activations Density 64.529%

    No Known Activations