© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10611
    Prev
    Next
    INDEX
    Explanations

    a variety of tokens that include code, Russian words, measurements of microns, and words related to government.

    oai_token-act-pair · gemini-2.0-flash

    prefixes and patterns in both English and Russian

    np_token-act-pair-logits · gpt-4o-mini

    Code snippets/symbols

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    Datuak
    -1.05
    ########.
    -0.90
     onPostExecute
    -0.81
     AppColors
    -0.80
     CGSize
    -0.79
     AttributeSet
    -0.79
     contextLoads
    -0.78
     démission
    -0.77
     getHeight
    -0.77
     getCode
    -0.74
    POSITIVE LOGITS
     sez
    0.35
     prod
    0.34
     epithe
    0.34
     де
    0.33
     pro
    0.32
     sou
    0.32
     J
    0.32
     fale
    0.30
    лу
    0.30
     ces
    0.30
    Activations Density 0.137%

    No Known Activations