© 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. 12022
    Prev
    Next
    INDEX
    Explanations

    German text containing verbs and related grammatical structures.

    oai_token-act-pair · gemini-2.0-flash

    German language text

    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
    elry
    -0.47
     Offisielt
    -0.46
    niająca
    -0.46
    alty
    -0.45
    bish
    -0.45
    otypic
    -0.44
    optera
    -0.44
    olson
    -0.44
     precedence
    -0.43
    Stevie
    -0.43
    POSITIVE LOGITS
     kasarigan
    0.74
    RegressionTest
    0.68
    MockBean
    0.63
    SourceChecksum
    0.61
    tagext
    0.60
     createState
    0.56
    FieldBuilder
    0.55
    GroupLayout
    0.54
    CodeAttribute
    0.54
    HtmlAttribute
    0.54
    Activations Density 0.326%

    No Known Activations