© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 11354
    Prev
    Next
    INDEX
    Explanations

    words and phrases that appear in formal writing

    oai_token-act-pair · gemini-2.0-flash

    Formal, mixed documents

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     end
    -0.91
     mid
    -0.75
     End
    -0.65
    end
    -0.65
    End
    -0.63
     Mid
    -0.61
    mid
    -0.60
    Mid
    -0.54
     anti
    -0.53
    aud
    -0.53
    POSITIVE LOGITS
    bootstrapcdn
    0.84
    RectangleBorder
    0.79
     تضيفلها
    0.77
    WriteTagHelper
    0.71
    tagHelperRunner
    0.68
     pinulongan
    0.68
    elemField
    0.68
     '\\;'
    0.68
     ModelExpression
    0.65
    MLLoader
    0.63
    Activations Density 1.021%

    No Known Activations