© 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. 9052
    Prev
    Next
    INDEX
    Explanations

    German language using certain grammatical structures like infinitive verb chains and modal verbs

    oai_token-act-pair · gemini-2.0-flash

    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_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
     EconPapers
    -0.79
     <",
    -0.73
    ConstraintMaker
    -0.73
    .},
    -0.73
    Personensuche
    -0.72
    MessageOf
    -0.71
    AndEndTag
    -0.71
    +#+#
    -0.69
     فريبيس
    -0.69
     سكانية
    -0.66
    POSITIVE LOGITS
    ställning
    0.64
    vänt
    0.63
    vangen
    0.62
    leggen
    0.60
    föra
    0.59
    zonder
    0.58
    strij
    0.57
    delning
    0.57
    wezig
    0.56
    kész
    0.56
    Activations Density 0.768%

    No Known Activations