© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 10780
    Prev
    Next
    INDEX
    Explanations

    code snippets with hexadecimal values and labels like "cur", "idx", "xf", or "xc"

    oai_token-act-pair · gemini-2.0-flash

    3

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    ]--;
    -0.99
    AndEndTag
    -0.96
    :✨
    -0.89
    UnusedPrivate
    -0.83
     Cæsar
    -0.79
    ]='\
    -0.76
     يتيمه
    -0.74
    #+#
    -0.74
     kasarigan
    -0.74
    Vidite
    -0.72
    POSITIVE LOGITS
     is
    0.48
     semej
    0.48
    prepareStatement
    0.48
     We
    0.41
     a
    0.40
     
    0.39
     into
    0.39
     szem
    0.37
     (
    0.37
    UrlResolution
    0.37
    Activations Density 3.770%

    No Known Activations