© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11384
    Prev
    Next
    INDEX
    Explanations

    words related to legal and financial terminology

    oai_token-act-pair · gemini-2.0-flash

    legal terminology and contract-related words

    np_token-act-pair-logits · gpt-4o-mini

    legal documents

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     GenerationType
    -0.70
    AsUp
    -0.63
    Życiorys
    -0.55
    ніципа
    -0.53
    нансо
    -0.53
     Schilling
    -0.52
    {!!
    -0.52
    +:+
    -0.52
    kloped
    -0.51
     OMITBAD
    -0.51
    POSITIVE LOGITS
     själva
    0.50
     ganha
    0.44
     ***!
    0.44
    BaseAdapter
    0.44
    🗳
    0.43
     reserved
    0.43
     dipende
    0.42
     themselves
    0.42
     can
    0.42
     próprios
    0.42
    Activations Density 7.627%

    No Known Activations