© 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. 12295
    Prev
    Next
    INDEX
    Explanations

    legal terminology and phrases often found in legal documents.

    oai_token-act-pair · gemini-2.0-flash

    technical or specialized terms

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

    Legal claims and damages

    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
    word
    -0.45
     Er
    -0.40
     dø
    -0.40
    law
    -0.39
    лоди
    -0.39
    Word
    -0.37
    Er
    -0.36
     Muro
    -0.36
    or
    -0.35
    ese
    -0.35
    POSITIVE LOGITS
    interopRequire
    0.88
    LookAnd
    0.85
     Савезне
    0.84
    WriteBarrier
    0.79
    ImageContext
    0.78
     متعلقه
    0.78
    OGND
    0.75
     Monfieur
    0.73
     purpoſe
    0.72
    ---*/
    0.71
    Activations Density 4.447%

    No Known Activations