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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 14926
    Prev
    Next
    INDEX
    Explanations

    German sentences that discuss modal verbs and give examples of their usage

    oai_token-act-pair · gemini-2.0-flash

    uncommon or unique prefixes and terms

    np_token-act-pair-logits · gpt-4o-mini

    foreign language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    RegressionTest
    -0.95
    Personensuche
    -0.78
    AnchorStyles
    -0.74
    #
    -0.68
    SpringBootTest
    -0.68
    --)
    -0.67
    UnknownFields
    -0.63
     '',
    -0.63
    TagMode
    -0.62
    "):
    -0.62
    POSITIVE LOGITS
     فريبيس
    0.41
     umbi
    0.41
    janya
    0.40
     Bel
    0.38
     passe
    0.38
    Passe
    0.37
    ########.
    0.36
    ことになる
    0.35
    englanniksi
    0.35
     SafeMath
    0.35
    Activations Density 0.387%

    No Known Activations