© 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. 3899
    Prev
    Next
    INDEX
    Explanations

    phrases indicating conversational tone and opinion

    oai_token-act-pair · gemini-2.0-flash

    tokens from technical or coding contexts

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

    punctuation

    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
    well
    -0.75
     well
    -0.67
    WELL
    -0.66
    Well
    -0.60
     its
    -0.56
     WELL
    -0.55
    its
    -0.54
    wells
    -0.51
    Its
    -0.51
    thats
    -0.50
    POSITIVE LOGITS
     autorytatywna
    0.68
    ngdoc
    0.65
    ContentAsync
    0.64
    +#+#
    0.64
     وتسجيلات
    0.59
    RegistryLite
    0.59
     pinulongan
    0.59
    oredCriteria
    0.59
    AndEndTag
    0.59
    ExtendWith
    0.58
    Activations Density 0.965%

    No Known Activations