© 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. 14590
    Prev
    Next
    INDEX
    Explanations

    Danish words and phrases, especially those related to film titles, familial relationships ('far' = father), and endearment ('Kærlighed' = love)

    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
    Autoritní
    -0.63
     AssemblyTitle
    -0.56
    ритори
    -0.56
     &___
    -0.52
    kilde
    -0.49
     newBuilder
    -0.49
    kable
    -0.49
     Dike
    -0.48
    FontOfSize
    -0.47
     الرياضيه
    -0.47
    POSITIVE LOGITS
     gynhyrchwyd
    0.71
     ansatte
    0.65
     skolen
    0.60
    LookAnd
    0.59
     utford
    0.56
     politiet
    0.55
    DoubleQuotes
    0.55
    enumii
    0.55
     glyphicon
    0.54
     samfun
    0.54
    Activations Density 0.477%

    No Known Activations