© 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. 7132
    Prev
    Next
    INDEX
    Explanations

    descriptive language used in product descriptions

    oai_token-act-pair · gemini-2.0-flash

    technical terms related to materials or functionality

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

    product features

    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
    Personendaten
    -0.56
    хьтан
    -0.54
    BeginContext
    -0.54
    日報
    -0.50
    pacs
    -0.49
     stuk
    -0.49
    contentLoaded
    -0.49
    évaluateur
    -0.48
     ffilmiau
    -0.48
     Exactos
    -0.47
    POSITIVE LOGITS
     '\\;'
    0.60
     InputDecoration
    0.59
     cast
    0.59
     ModelAndView
    0.59
     durable
    0.55
     stainless
    0.55
     Stainless
    0.53
     muualla
    0.52
    Stainless
    0.52
     resultCode
    0.52
    Activations Density 1.380%

    No Known Activations