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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 7054
    Prev
    Next
    INDEX
    Explanations

    legal and psychological jargon

    oai_token-act-pair · gemini-2.0-flash

    words associated with legal or judicial contexts

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

    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_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
    tvguidetime
    -0.94
     ujednoznacz
    -0.94
     doInBackground
    -0.87
    StructEnd
    -0.86
     متعلقه
    -0.84
    MLLoader
    -0.82
     EconPapers
    -0.81
     Réponses
    -0.81
    ReusableCell
    -0.81
     Efq
    -0.80
    POSITIVE LOGITS
     en
    0.47
    En
    0.46
    tir
    0.45
    en
    0.42
     u
    0.42
     En
    0.42
    ted
    0.40
    ken
    0.39
    �
    0.38
    ual
    0.38
    Activations Density 2.454%

    No Known Activations