© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 1952
    Prev
    Next
    INDEX
    Explanations

    code snippets, especially Java, XML and possibly some template languages

    oai_token-act-pair · gemini-2.0-flash

    say colon or equals sign

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    makeText
    -0.54
     mode
    -0.50
    tichetta
    -0.50
    me
    -0.47
     me
    -0.47
     und
    -0.46
     her
    -0.46
     su
    -0.46
     hit
    -0.46
     StringTokenizer
    -0.46
    POSITIVE LOGITS
     tartalomajánló
    0.78
     فريبيس
    0.78
     Reſ
    0.63
     Phry
    0.61
     الحره
    0.61
    DataAnnotations
    0.61
    InSection
    0.61
    SequentialGroup
    0.60
    RetentionPolicy
    0.60
     Poto
    0.59
    Activations Density 3.887%

    No Known Activations