© 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. 13310
    Prev
    Next
    INDEX
    Explanations

    code examples with comments containing portuguese words

    oai_token-act-pair · gemini-2.0-flash

    words starting with special characters or unusual letters

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

    code and mixed languages

    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
    gbarkeit
    -0.43
     t
    -0.41
     p
    -0.41
    -
    -0.39
    теристи
    -0.38
    Flint
    -0.37
     b
    -0.37
     fil
    -0.35
     ni
    -0.35
     отношению
    -0.35
    POSITIVE LOGITS
     Efq
    1.01
     ſch
    0.90
     Monfieur
    0.85
     Majefty
    0.85
     myſelf
    0.84
     ſmall
    0.84
     pleaſure
    0.84
     Diſ
    0.83
     laſt
    0.82
     whoſe
    0.82
    Activations Density 0.309%

    No Known Activations