© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12474
    Prev
    Next
    INDEX
    Explanations

    sentences that state a fact, especially using "is."

    oai_token-act-pair · gemini-2.0-flash

    variations of the word "possible"

    np_token-act-pair-logits · gpt-4o-mini

    is

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     it
    -1.09
     оно
    -0.96
    它
    -0.88
     它
    -0.81
     It
    -0.79
    It
    -0.75
     nó
    -0.66
    它是
    -0.66
    it
    -0.61
     которое
    -0.60
    POSITIVE LOGITS
     possible
    1.59
    possible
    1.39
    Possible
    1.33
     poffible
    1.30
     Possible
    1.29
     POSSIBLE
    1.26
     posible
    1.16
     conceivable
    1.09
     necessary
    1.08
    POSSIBLE
    1.07
    Activations Density 6.062%

    No Known Activations