© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 5782
    Prev
    Next
    INDEX
    Explanations

    Spanish and Javascript code snippets with variable manipulation

    oai_token-act-pair · gemini-2.0-flash

    lo

    np_max-act · gemini-2.0-flash

    Spanish determiners

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     CiNii
    -0.73
     sagesse
    -0.66
    olesale
    -0.65
     Houſe
    -0.63
    ]")]
    -0.63
     Souhaitez
    -0.63
    prow
    -0.63
    NullException
    -0.62
     Ressources
    -0.62
    carbonate
    -0.62
    POSITIVE LOGITS
    aarrggbb
    0.73
     Our
    0.69
    Our
    0.66
     Ours
    0.62
    Ours
    0.61
     our
    0.59
     OUR
    0.59
     your
    0.55
     the
    0.55
    the
    0.55
    Activations Density 0.234%

    No Known Activations