© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 7607
    Prev
    Next
    INDEX
    Explanations

    German verbs, particularly auxiliary verbs and past participles, within complex sentence structures.

    oai_token-act-pair · gemini-2.0-flash

    German/code fragments

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.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
     Administrativna
    -0.68
    berdayakan
    -0.66
    onViewCreated
    -0.63
    PreferredItem
    -0.61
     Grecs
    -0.60
     متعلقه
    -0.58
    Personensuche
    -0.58
    }],
    -0.56
    الإنجليزية
    -0.56
    ("")]
    -0.56
    POSITIVE LOGITS
     worden
    0.57
    setVerticalGroup
    0.56
     zost
    0.55
     được
    0.52
     soon
    0.49
     zostanie
    0.48
     werden
    0.47
    MathML
    0.46
     being
    0.45
     CURIAM
    0.45
    Activations Density 0.399%

    No Known Activations