© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 10019
    Prev
    Next
    INDEX
    Explanations

    sequences of capital letters, sometimes followed by numbers, and sometimes mixed in with other words

    oai_token-act-pair · gemini-2.0-flash

    code identifiers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    antaranya
    -0.72
     صوتيه
    -0.67
     tartalomajánló
    -0.67
    harapkan
    -0.66
     plainte
    -0.65
     témoins
    -0.65
    berdayakan
    -0.65
    istocene
    -0.64
    runApp
    -0.64
     gratuitas
    -0.63
    POSITIVE LOGITS
    nal
    0.68
     Na
    0.68
     na
    0.68
    nam
    0.65
    nak
    0.63
    Na
    0.62
     Nav
    0.61
     nav
    0.60
     Anal
    0.60
    NAL
    0.59
    Activations Density 0.200%

    No Known Activations