© 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. 6506
    Prev
    Next
    INDEX
    Explanations

    consecutive verbs in German

    oai_token-act-pair · gemini-2.0-flash

    technical/academic writing

    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
     calldata
    -0.48
    vierte
    -0.48
     GreatSchools
    -0.47
    DrawerLayout
    -0.45
    ichtlich
    -0.45
    ServletConfig
    -0.45
     Lightboxes
    -0.44
    HideInInspector
    -0.44
    viewWillAppear
    -0.43
    GEBURTSDATUM
    -0.43
    POSITIVE LOGITS
    TagMode
    0.69
     ujednoznacz
    0.63
     مشين
    0.61
     neuem
    0.56
     nakalista
    0.55
     interesan
    0.55
     saites
    0.55
     fáciles
    0.55
     falschen
    0.54
     ewigen
    0.54
    Activations Density 0.780%

    No Known Activations