© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 14977
    Prev
    Next
    INDEX
    Explanations

    words, phrases, and punctuation commonly found in legal documents or legal arguments

    oai_token-act-pair · gemini-2.0-flash

    technical or code-related terms

    np_token-act-pair-logits · gpt-4o-mini
    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
     OFDb
    -0.56
     GenerationType
    -0.50
    AsUp
    -0.47
     then
    -0.44
     Chamber
    -0.44
     Kamer
    -0.43
     Потом
    -0.42
    findOneAndUpdate
    -0.42
    reactstrap
    -0.41
     CHAMBER
    -0.40
    POSITIVE LOGITS
     resourceCulture
    0.66
    انجليز
    0.63
    لينكات
    0.63
    BitmapFactory
    0.63
    fjspx
    0.61
     <<<<<<<<<<<<<<
    0.58
    CreateMap
    0.57
     siquiera
    0.56
    DebuggerNonUser
    0.55
     AssemblyCulture
    0.55
    Activations Density 5.811%

    No Known Activations