© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 13077
    Prev
    Next
    INDEX
    Explanations

    angle brackets and words from languages other than English, particularly words related to privacy, terms and agreements, phone numbers and accounts

    oai_token-act-pair · gemini-2.0-flash

    Code snippets/data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    GEBURTSDATUM
    -1.13
    PerformLayout
    -1.03
    httphttps
    -0.87
     betweenstory
    -0.86
     CURIAM
    -0.86
    +#+#
    -0.84
    parsedMessage
    -0.83
    sizeCache
    -0.82
    LookAnd
    -0.80
    ########.
    -0.79
    POSITIVE LOGITS
    раздо
    0.50
    らしい
    0.46
     bezit
    0.45
    ↵
    0.44
     but
    0.44
     manquer
    0.44
     rapporto
    0.43
    gten
    0.43
     &
    0.42
     relação
    0.42
    Activations Density 11.509%

    No Known Activations