© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6658
    Prev
    Next
    INDEX
    Explanations

    a mix of personal pronouns ("I", "you", "they"), conjunctions ("and", "but"), and verbs related to leading/working/evaluating.

    oai_token-act-pair · gemini-2.0-flash

    teaching

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.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
    脚注の使い方
    -0.68
    +:+
    -0.55
    ArgsConstructor
    -0.52
    SpringBootTest
    -0.52
    TypedDataSet
    -0.52
    béco
    -0.52
    typeorm
    -0.50
    نین
    -0.50
    Datuak
    -0.49
    存于互联网档案馆
    -0.49
    POSITIVE LOGITS
     teaching
    0.91
     instructing
    0.88
     teach
    0.88
     Teaching
    0.88
     encourage
    0.85
     Teach
    0.84
    Teaching
    0.84
    teaching
    0.82
     Encourage
    0.81
     recruiting
    0.81
    Activations Density 2.185%

    No Known Activations