© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 9792
    Prev
    Next
    INDEX
    Explanations

    programming code and scientific paper snippets

    oai_token-act-pair · gemini-2.0-flash

    mutations

    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
     withal
    -0.88
    GraphicsUnit
    -0.77
    webElementGuid
    -0.71
    #+#
    -0.70
     тоже
    -0.69
    Diweddarwch
    -0.68
    Zeneca
    -0.67
     demurrer
    -0.66
     alfo
    -0.65
     Josephus
    -0.64
    POSITIVE LOGITS
    Jîn
    0.52
     <=",
    0.43
    ligible
    0.42
     allein
    0.42
    lowski
    0.41
    rtype
    0.39
    swing
    0.39
     trajets
    0.38
     gre
    0.38
    anci
    0.38
    Activations Density 6.294%

    No Known Activations