© 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
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 5077
    Prev
    Next
    INDEX
    Explanations

    the word "lies" or the phrase "[something] stands", as well as some other verbs that can be used to relate ideas.

    oai_token-act-pair · gemini-2.0-flash

    technical terms or concepts

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

    say prepositions

    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
    AddTagHelper
    -0.75
    новниш
    -0.72
    UIControlState
    -0.71
     chofe
    -0.69
     Theſe
    -0.68
     tartalomajánló
    -0.67
    вгений
    -0.66
    ValueGeneration
    -0.65
    }{*}{}
    -0.65
    archiviato
    -0.65
    POSITIVE LOGITS
     just
    0.44
     clearfix
    0.42
     ujednoznacz
    0.42
    maxn
    0.41
    styleType
    0.40
     OnInit
    0.40
    φα
    0.39
     ekster
    0.39
     kés
    0.39
    UNDLE
    0.38
    Activations Density 1.616%

    No Known Activations