© 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. 5968
    Prev
    Next
    INDEX
    Explanations

    Korean names

    oai_token-act-pair · gemini-2.0-flash

    Korean names

    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
    WireFormatLite
    -0.75
    ClientSize
    -0.75
     Italijanski
    -0.69
     تكبرها
    -0.69
    SizeF
    -0.66
    WithIOException
    -0.65
    intios
    -0.64
    NameInMap
    -0.63
    UnusedPrivate
    -0.63
    felves
    -0.63
    POSITIVE LOGITS
    hye
    0.47
    shin
    0.47
    hyo
    0.46
    hy
    0.45
     TAMBÉM
    0.45
    haru
    0.44
    miu
    0.44
    hb
    0.44
    suk
    0.44
     Soo
    0.43
    Activations Density 4.440%

    No Known Activations