© 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. 6061
    Prev
    Next
    INDEX
    Explanations

    code and non-English text

    oai_token-act-pair · gemini-2.0-flash

    Code and 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
     and
    -0.49
     незавершена
    -0.46
    Gön
    -0.45
    WireFormatLite
    -0.45
    utives
    -0.44
    glLoadIdentity
    -0.41
    сылкі
    -0.41
     chi̍t
    -0.40
     تانيه
    -0.40
    futbolista
    -0.39
    POSITIVE LOGITS
     godine
    0.68
     Lordships
    0.65
     >=",
    0.60
     calendriers
    0.59
     apie
    0.59
     kuid
    0.58
     dikutip
    0.57
     তারিখ
    0.57
     rayos
    0.56
     kurie
    0.56
    Activations Density 3.728%

    No Known Activations