© 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. 7383
    Prev
    Next
    INDEX
    Explanations

    hyphenated words and surrounding context.

    oai_token-act-pair · gemini-2.0-flash

    -

    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
    исленность
    -0.65
    ioutil
    -0.62
     فريبيس
    -0.58
    SharedDtor
    -0.58
    d
    -0.55
    Vidite
    -0.54
    how
    -0.54
    mybatisplus
    -0.54
    PageIndex
    -0.53
    ticing
    -0.52
    POSITIVE LOGITS
    an
    0.89
    AN
    0.80
     cérami
    0.79
     juridiques
    0.70
     pédagog
    0.69
     dignité
    0.69
     dépens
    0.68
     pitié
    0.67
     foncé
    0.67
     consommateurs
    0.67
    Activations Density 15.891%

    No Known Activations