© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 1916
    Prev
    Next
    INDEX
    Explanations

    code and indentation from Java or similar programming language

    oai_token-act-pair · gemini-2.0-flash

    instances of the word 'DEAD'

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

    Code and special characters

    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
     disambiguazione
    -0.89
     Critical
    -0.85
    Critical
    -0.81
    critical
    -0.80
    دانشنامهٔ
    -0.79
     ExecuteAsync
    -0.77
     critical
    -0.77
     createContext
    -0.72
    DockStyle
    -0.72
    CloseOperation
    -0.71
    POSITIVE LOGITS
     must
    0.45
     V
    0.42
    дол
    0.41
    roned
    0.41
    bör
    0.41
     tra
    0.41
                                   
    0.41
     pe
    0.40
     referenties
    0.40
    SequentialGroup
    0.40
    Activations Density 1.439%

    No Known Activations