© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 9944
    Prev
    Next
    INDEX
    Explanations

    the word "magic", sometimes with a number nearby or the abbreviation "etc"

    oai_token-act-pair · gemini-2.0-flash

    magic

    np_max-act · gemini-2.0-flash
    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
     aikaa
    -0.86
     cappello
    -0.82
     héri
    -0.81
    UnusedPrivate
    -0.80
     precisione
    -0.78
     chêne
    -0.77
     feroit
    -0.77
     fratelli
    -0.76
     citoy
    -0.76
     coraggio
    -0.76
    POSITIVE LOGITS
     cote
    0.68
     background
    0.66
     flow
    0.65
     layer
    0.65
     fix
    0.65
     screen
    0.64
     kik
    0.64
     mena
    0.62
     mati
    0.62
     spot
    0.62
    Activations Density 2.720%

    No Known Activations