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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 9934
    Prev
    Next
    INDEX
    Explanations

    words related to family background and personal history, often including possessive pronouns and names

    oai_token-act-pair · gemini-2.0-flash

    say "name"

    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
     S
    -0.63
    UnusedPrivate
    -0.63
     дописавши
    -0.63
    urlpatterns
    -0.59
    ISupport
    -0.55
     PublicKey
    -0.55
    ="#"><
    -0.54
     CreateTagHelper
    -0.52
     AssemblyCompany
    -0.52
    complexType
    -0.50
    POSITIVE LOGITS
     last
    2.58
    last
    2.25
    Last
    2.16
     Last
    2.14
     LAST
    1.85
    LAST
    1.82
     último
    1.59
     letzten
    1.52
     última
    1.52
     últimos
    1.50
    Activations Density 3.509%

    No Known Activations