© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 15452
    Prev
    Next
    INDEX
    Explanations

    hexadecimal color codes

    oai_token-act-pair · gemini-2.0-flash

    Code snippets and hex data

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    yaitu
    -0.51
     whoſe
    -0.50
     onely
    -0.49
     Efq
    -0.48
     himſelf
    -0.48
     myſelf
    -0.48
    bibinfo
    -0.47
     Ее
    -0.47
     againſt
    -0.47
    NoStop
    -0.46
    POSITIVE LOGITS
    TagMode
    0.93
    tagHelperRunner
    0.81
    AddHtmlAttribute
    0.81
    IsContent
    0.77
    ScopeManager
    0.76
    msgTypes
    0.75
    SequentialGroup
    0.75
    XMLSchema
    0.72
     defaultstate
    0.71
    principalColumn
    0.71
    Activations Density 16.401%

    No Known Activations