© 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. 7336
    Prev
    Next
    INDEX
    Explanations

    legal jargon related to warranties.

    oai_token-act-pair · gemini-2.0-flash

    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_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
     CO
    -1.70
    CO
    -1.49
     PO
    -1.30
     HO
    -1.23
    HO
    -1.23
    PO
    -1.21
    SO
    -1.20
     RO
    -1.20
     LO
    -1.20
     SO
    -1.17
    POSITIVE LOGITS
     surla
    0.59
    QMetaType
    0.56
    ATN
    0.53
    kse
    0.50
     Rei
    0.50
     Efe
    0.47
    audiovisuel
    0.46
    EDEFAULT
    0.46
    Демографія
    0.45
     Kraj
    0.45
    Activations Density 3.285%

    No Known Activations