© 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. 10143
    Prev
    Next
    INDEX
    Explanations

    terms from several programming languages including Javascript, PHP, and C

    oai_token-act-pair · gemini-2.0-flash

    Portuguese (programming)

    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
    Atentamente
    -1.74
    convite
    -1.53
    Conteúdo
    -1.49
    Reprodução
    -1.44
    igreja
    -1.44
    Dimensões
    -1.44
    Procedimiento
    -1.42
    Parabéns
    -1.41
    Observaciones
    -1.40
    Pacote
    -1.38
    POSITIVE LOGITS
    A
    0.91
    Pa
    0.89
    No
    0.89
    Do
    0.84
    Con
    0.83
    Com
    0.82
    In
    0.82
    return
    0.81
    Imp
    0.81
     poffe
    0.80
    Activations Density 0.657%

    No Known Activations