© 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
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 8841
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to sharing, breaks, and parenting.

    oai_token-act-pair · gemini-2.0-flash

    Personal/emotional writing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     CWE
    -0.72
     endwhile
    -0.68
     الحره
    -0.68
     FormBuilder
    -0.67
    CodeAttribute
    -0.67
     étoient
    -0.67
    __":
    -0.66
    InjectAttribute
    -0.65
    ysuckle
    -0.64
     كومونز
    -0.64
    POSITIVE LOGITS
    ValueStyle
    0.41
    SpringBootTest
    0.40
    Response
    0.40
    krivelse
    0.40
    sizePolicy
    0.39
    oredCriteria
    0.39
    PROLOG
    0.38
    lin
    0.38
    سلام
    0.38
     time
    0.37
    Activations Density 7.273%

    No Known Activations