© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 12155
    Prev
    Next
    INDEX
    Explanations

    adjective noun pairs

    oai_token-act-pair · gemini-2.0-flash

    article a/an

    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
    featureID
    -0.69
     nakalista
    -0.66
    XmlAccessType
    -0.61
    andExpect
    -0.59
    تقاوى
    -0.59
    ImageContext
    -0.57
    पया
    -0.55
    writeFieldEnd
    -0.53
     MenuView
    -0.52
    AddHtmlAttribute
    -0.52
    POSITIVE LOGITS
     newOwner
    0.56
    migrationBuilder
    0.55
    SupportActionBar
    0.54
     MessageBoxIcon
    0.51
     useParams
    0.50
    GenerationType
    0.48
     imageNamed
    0.48
     useDispatch
    0.48
    BindingResult
    0.48
     isolation
    0.48
    Activations Density 1.619%

    No Known Activations