© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 3972
    Prev
    Next
    INDEX
    Explanations

    words related to legal cases and user reviews of software.

    oai_token-act-pair · gemini-2.0-flash

    legal context

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     avoient
    -0.88
     myſelf
    -0.87
     ainfi
    -0.86
    AndEndTag
    -0.84
     étoient
    -0.83
     Efq
    -0.82
     feroit
    -0.80
     démocratie
    -0.79
     ―――――
    -0.78
     itſelf
    -0.78
    POSITIVE LOGITS
     same
    0.98
     final
    0.87
     second
    0.85
     situation
    0.78
     role
    0.78
     entire
    0.76
     latest
    0.75
     base
    0.75
     portion
    0.74
     list
    0.73
    Activations Density 9.301%

    No Known Activations