© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 4853
    Prev
    Next
    INDEX
    Explanations

    the substrings "mer", "aris", "ica", "ipi", "cor", and Italian institutions, particularly those in Pisa.

    oai_token-act-pair · gemini-2.0-flash

    scientific materials

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    <bos>
    -0.94
     zufolge
    -0.77
    Cordialement
    -0.76
     publiques
    -0.74
    ArrowToggle
    -0.70
    Égypte
    -0.70
    Ранее
    -0.68
     giusti
    -0.67
     étoient
    -0.67
    Архівовано
    -0.67
    POSITIVE LOGITS
    TestingModule
    0.62
    ThroughAttribute
    0.58
     resourceCulture
    0.58
    而不
    0.57
    bonucle
    0.57
     irre
    0.56
     tre
    0.52
    ksikon
    0.52
    Tre
    0.52
     lik
    0.50
    Activations Density 0.193%

    No Known Activations