© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3041
    Prev
    Next
    INDEX
    Explanations

    Russian language related to computer programming

    oai_token-act-pair · gemini-2.0-flash

    words related to programming and string manipulation

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

    Slavic languages/code

    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
     Efq
    -0.93
    IVEREF
    -0.88
     Italijanski
    -0.86
     Monfieur
    -0.83
    oredCriteria
    -0.83
     Савезне
    -0.82
     Walkover
    -0.81
    AsUp
    -0.80
     Jefus
    -0.78
     Theſe
    -0.77
    POSITIVE LOGITS
    gese
    0.45
    pha
    0.44
    Петер
    0.43
    ządu
    0.41
    antor
    0.41
    acu
    0.41
    otu
    0.40
    odu
    0.40
    const
    0.40
    吒
    0.39
    Activations Density 0.318%

    No Known Activations