© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 1970
    Prev
    Next
    INDEX
    Explanations

    complex sentence fragments including conjunctions and words related to software and cars

    oai_token-act-pair · gemini-2.0-flash

    doing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     використову
    -0.52
     memoized
    -0.49
    AndEndTag
    -0.49
     нажмите
    -0.45
    isert
    -0.43
    UserScript
    -0.41
     ++)
    -0.40
    SharedDtor
    -0.40
     bertujuan
    -0.40
    RefNanny
    -0.39
    POSITIVE LOGITS
     getting
    1.45
     taking
    1.30
     obtaining
    1.29
     acquiring
    1.27
     having
    1.27
     doing
    1.23
     keeping
    1.23
     making
    1.23
     finding
    1.21
     putting
    1.21
    Activations Density 2.953%

    No Known Activations