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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 12-GEMMASCOPE-TRANSCODER-16K
    4. 12811
    Prev
    Next
    INDEX
    Explanations

    questions regarding the process of writing and creation, especially concerning inspiration and future projects

    oai_token-act-pair · gemini-2.0-flash

    process/evolve

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    <bos>
    -0.59
    scha
    -0.54
    dev
    -0.53
    JAC
    -0.51
    мите
    -0.48
    Fig
    -0.48
    VALIDATE
    -0.47
     mechan
    -0.46
    ди
    -0.46
    pha
    -0.46
    POSITIVE LOGITS
    SpringBootTest
    0.89
    ValueStyle
    0.89
    tvguidetime
    0.86
    脚注の使い方
    0.83
    GraphicsUnit
    0.77
     snippetHide
    0.77
     MainAxisSize
    0.75
    XmlAccessType
    0.75
    InstanceState
    0.75
     AttributeSet
    0.75
    Activations Density 0.120%

    No Known Activations