© 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. 1097
    Prev
    Next
    INDEX
    Explanations

    words, names, and places pertaining to German and Scandinavian history and geography.

    oai_token-act-pair · gemini-2.0-flash

    German

    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
     propOrder
    -0.67
     متعلقه
    -0.63
     TextAppearance
    -0.60
    tagHelperRunner
    -0.59
    )++;
    -0.57
    PerformLayout
    -0.56
    GenerationType
    -0.55
    Personendaten
    -0.52
    StoryboardSegue
    -0.52
     himo
    -0.52
    POSITIVE LOGITS
    hofer
    0.47
    Sch
    0.47
    hofen
    0.46
     tedes
    0.45
    German
    0.44
    schw
    0.44
    weg
    0.43
    hof
    0.42
     Germans
    0.42
     Schle
    0.41
    Activations Density 18.963%

    No Known Activations