© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 15038
    Prev
    Next
    INDEX
    Explanations

    locations and organizations

    oai_token-act-pair · gemini-2.0-flash

    diverse vocabulary

    np_max-act · gemini-2.0-flash

    say "punctuation or capitalized"

    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_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    ภัณฑ์
    -0.52
     suffices
    -0.49
     enough
    -0.49
    ly
    -0.46
    asions
    -0.46
    льга
    -0.45
    umpf
    -0.45
     Púb
    -0.44
     والث
    -0.44
     хо
    -0.43
    POSITIVE LOGITS
    ">//
    1.00
    تقاوى
    0.96
     nahilalakip
    0.94
     lenker
    0.92
     beginnetje
    0.87
    EDEFAULT
    0.86
     كومونز
    0.85
    parsedMessage
    0.81
     createState
    0.81
    LookAnd
    0.77
    Activations Density 18.384%

    No Known Activations