© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 807
    Prev
    Next
    INDEX
    Explanations

    conjunctions and words implying causality ('because', 'since')

    oai_token-act-pair · gemini-2.0-flash

    reasons and explanations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     للاسماء
    -0.67
    routeProvider
    -0.59
     imprimée
    -0.57
     arroyo
    -0.57
    alou
    -0.57
     Honours
    -0.56
     myſelf
    -0.56
     préfé
    -0.55
     agré
    -0.54
     ostrich
    -0.54
    POSITIVE LOGITS
     دیکھیے
    0.75
    webElementGuid
    0.61
     الرياضيه
    0.59
    Související
    0.53
    хьтан
    0.51
    љено
    0.51
     springfox
    0.50
     ses
    0.49
     bec
    0.48
    tvguidetime
    0.48
    Activations Density 1.741%

    No Known Activations