© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12539
    Prev
    Next
    INDEX
    Explanations

    words related to negative opinions, judgements, or assessments.

    oai_token-act-pair · gemini-2.0-flash

    legal criticism

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    toFloat
    -0.52
     houſe
    -0.52
     mede
    -0.52
     Houſe
    -0.50
     sorrows
    -0.48
     Diſ
    -0.47
     daihatsu
    -0.47
     financiar
    -0.47
     capilar
    -0.47
    ulante
    -0.47
    POSITIVE LOGITS
     practice
    0.98
     PRACTICE
    0.85
     Practice
    0.85
     practise
    0.84
    practice
    0.84
     PRACT
    0.82
     resourceCulture
    0.79
     springfox
    0.79
    PRACTICE
    0.78
    Practice
    0.77
    Activations Density 0.642%

    No Known Activations