© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 5043
    Prev
    Next
    INDEX
    Explanations

    instances of "can" where the speaker is describing what they are able to perceive or do

    oai_token-act-pair · gemini-2.0-flash

    can

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    Spoljašnje
    -0.58
     "..\..\
    -0.57
    enumi
    -0.55
    twimg
    -0.55
     EventEmitter
    -0.54
    /**
    -0.54
     EconPapers
    -0.52
     pinulongan
    -0.52
    CLUYE
    -0.51
     jsPsych
    -0.51
    POSITIVE LOGITS
     tell
    2.47
     Tell
    2.25
     telling
    2.25
    Tell
    2.22
    tell
    2.09
     TELL
    2.03
     Telling
    1.93
     tells
    1.92
    tells
    1.88
    telling
    1.88
    Activations Density 3.183%

    No Known Activations