© 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. 12461
    Prev
    Next
    INDEX
    Explanations

    future tense sentences starting with "We"

    oai_token-act-pair · gemini-2.0-flash

    verbs indicating future actions

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

    intended actions/future events

    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
     intptr
    -0.54
     /\.
    -0.52
     EClass
    -0.51
    UserScript
    -0.48
    ніципа
    -0.48
    ruptedException
    -0.47
    })]
    -0.46
    AddTagHelper
    -0.45
    ыгана
    -0.45
    RectangleBorder
    -0.45
    POSITIVE LOGITS
     communicates
    0.66
     Efq
    0.64
    IsContent
    0.63
    RegressionTest
    0.63
    NOPQRST
    0.60
     adapts
    0.60
     does
    0.59
     begins
    0.58
    cektir
    0.58
     commences
    0.57
    Activations Density 1.165%

    No Known Activations