© 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. 12007
    Prev
    Next
    INDEX
    Explanations

    examples in multiple languages

    oai_token-act-pair · gemini-2.0-flash

    Ich

    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
    +#+#
    -0.43
     đáp
    -0.43
     оригіналу
    -0.42
    kell
    -0.42
     Bancroft
    -0.42
     vítima
    -0.42
    Hippo
    -0.41
    sfw
    -0.41
    lema
    -0.41
    imedia
    -0.40
    POSITIVE LOGITS
     EClass
    0.85
    ConstraintMaker
    0.79
    tonsoft
    0.76
    WriteTagHelper
    0.75
    NewUrlParser
    0.71
    ImageContext
    0.69
    HomeAsUpEnabled
    0.67
     متعلقه
    0.66
    Portály
    0.65
     HttpNotFound
    0.65
    Activations Density 0.073%

    No Known Activations