© 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. 10648
    Prev
    Next
    INDEX
    Explanations

    unicode characters

    oai_token-act-pair · gemini-2.0-flash

    words starting with 'u'

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

    u

    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
     Monfieur
    -0.81
     Jefus
    -0.79
    CPtr
    -0.78
     houſe
    -0.76
    AndEndTag
    -0.75
    AddTagHelper
    -0.75
     myſelf
    -0.75
    tagHelperRunner
    -0.75
     Efq
    -0.75
     ſtate
    -0.72
    POSITIVE LOGITS
     sel
    0.42
    タ
    0.41
     Sel
    0.40
     Mar
    0.40
     Hal
    0.40
     Ta
    0.39
    sel
    0.39
     SA
    0.39
    میزی
    0.38
     Sa
    0.38
    Activations Density 1.646%

    No Known Activations