© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 9831
    Prev
    Next
    INDEX
    Explanations

    complex German sentences with "Brief" (letter) and multiple verbs, often in the subjunctive.

    oai_token-act-pair · gemini-2.0-flash

    code and foreign languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    __':
    -0.63
    </thead>
    -0.59
    достатки
    -0.59
     MainAxisSize
    -0.57
     مشين
    -0.56
     متعلقه
    -0.56
    dengar
    -0.54
    NavController
    -0.52
    __":
    -0.51
     tendenza
    -0.51
    POSITIVE LOGITS
     be
    0.74
     generate
    0.65
     achieve
    0.64
     imitate
    0.63
     disambiguazione
    0.62
     produce
    0.61
     accommodate
    0.60
     deliver
    0.60
     marry
    0.60
     simulate
    0.59
    Activations Density 0.202%

    No Known Activations