© 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. 25-GEMMASCOPE-TRANSCODER-16K
    4. 14615
    Prev
    Next
    INDEX
    Explanations

    uses of first and second person pronouns that refer to the author or a user of software

    oai_token-act-pair · gemini-2.0-flash

    code and programming

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    :✨
    -0.85
    ftagPool
    -0.80
    ThroughAttribute
    -0.77
    AddHtmlAttribute
    -0.75
     Normdatei
    -0.73
    #+#
    -0.68
    WriteBarrier
    -0.68
    Atsauces
    -0.66
    sizeCache
    -0.65
     BorderSide
    -0.64
    POSITIVE LOGITS
     translateY
    0.51
     sqlSession
    0.51
     conductor
    0.49
     UserRepository
    0.49
    ритори
    0.47
    HomeController
    0.47
     duod
    0.46
     SqlParameter
    0.46
    ieste
    0.46
    Construction
    0.46
    Activations Density 9.643%

    No Known Activations