© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 13306
    Prev
    Next
    INDEX
    Explanations

    past tense action verbs frequently followed by "I" or "has"

    oai_token-act-pair · gemini-2.0-flash

    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
    locate
    -0.63
     relaxes
    -0.59
     deploying
    -0.56
     noemen
    -0.55
    provoking
    -0.55
    locating
    -0.54
     assigns
    -0.54
     localize
    -0.54
     assigning
    -0.53
    icating
    -0.52
    POSITIVE LOGITS
     виправивши
    0.86
    tagHelperRunner
    0.74
     disambiguazione
    0.71
    LEncoder
    0.70
     Wicidata
    0.60
    parsedMessage
    0.60
    httphttps
    0.59
     raiſ
    0.57
    RTDA
    0.57
     offered
    0.57
    Activations Density 1.406%

    No Known Activations