© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 2256
    Prev
    Next
    INDEX
    Explanations

    promotional material for Mario Badescu products

    oai_token-act-pair · gemini-2.0-flash

    Finnish words

    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
     iconFacebook
    -0.60
    imation
    -0.53
    BibitemShut
    -0.53
     estekak
    -0.52
    Demografie
    -0.52
    źródło
    -0.52
    ]--;
    -0.48
     placent
    -0.48
     venom
    -0.48
     produce
    -0.47
    POSITIVE LOGITS
     sī
    0.62
     väli
    0.54
     aikaa
    0.54
    fjspx
    0.54
     myö
    0.53
    BeginContext
    0.52
     keskus
    0.50
    <_>
    0.50
     näin
    0.49
    ugier
    0.49
    Activations Density 15.774%

    No Known Activations