© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11361
    Prev
    Next
    INDEX
    Explanations

    words ending in "ids" as well as the fragment "vag"

    oai_token-act-pair · gemini-2.0-flash

    word endings with "ids" ending

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     ProtoMessage
    -0.66
    ppich
    -0.57
     meille
    -0.54
     sayap
    -0.51
     mobilité
    -0.51
    ']").
    -0.50
     Everywhere
    -0.50
    CppMethod
    -0.50
     kommunen
    -0.49
     enví
    -0.49
    POSITIVE LOGITS
     المعيارى
    0.68
    GraphicsUnit
    0.67
    ます
    0.55
    antMatchers
    0.54
    consulté
    0.54
     ones
    0.54
     Réponses
    0.52
    COLN
    0.51
     åt
    0.50
    BorderFactory
    0.50
    Activations Density 0.243%

    No Known Activations