© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 13751
    Prev
    Next
    INDEX
    Explanations

    different languages

    oai_token-act-pair · gemini-2.0-flash

    Past tense verbs

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     would
    -0.85
    would
    -0.81
     will
    -0.75
     Would
    -0.71
     оригіналу
    -0.71
     fhould
    -0.71
     WOULD
    -0.66
    ShouldBe
    -0.66
     can
    -0.65
    exitRule
    -0.65
    POSITIVE LOGITS
     was
    0.95
     did
    0.94
     came
    0.91
     took
    0.90
     went
    0.87
     gave
    0.84
     began
    0.81
     ended
    0.79
    Did
    0.77
    did
    0.76
    Activations Density 0.499%

    No Known Activations