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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 23-GEMMASCOPE-TRANSCODER-16K
    7. 12387
    Prev
    Next
    INDEX
    Explanations

    words frequently found in product reviews of diapers for babies

    oai_token-act-pair · gemini-2.0-flash

    it

    np_max-act-logits · gemini-2.0-flash

    say "verbs"

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    ReusableCell
    -0.73
    StructEnd
    -0.60
     autorytatywna
    -0.59
    awaiter
    -0.58
    ագրություններ
    -0.58
    migrationBuilder
    -0.58
    UnknownFields
    -0.56
     Wikimédia
    -0.56
    ọi
    -0.54
    InitStruct
    -0.54
    POSITIVE LOGITS
     shifted
    0.60
    intios
    0.52
     ditutup
    0.52
    LookAnd
    0.52
     fine
    0.52
     Krakowie
    0.50
     clung
    0.49
    ósito
    0.48
    fine
    0.48
    lants
    0.48
    Activations Density 4.692%

    No Known Activations