© 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. 2602
    Prev
    Next
    INDEX
    Explanations

    Java GUI code

    oai_token-act-pair · gemini-2.0-flash

    programming-related syntax or structure

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

    Java code

    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
    脚注の使い方
    -0.71
    Personendaten
    -0.70
    ineno
    -0.68
    AutoField
    -0.54
     يتيمه
    -0.53
    帖最后由
    -0.53
    ukone
    -0.53
    PerformLayout
    -0.52
     ProtoMessage
    -0.52
    pædia
    -0.50
    POSITIVE LOGITS
    __":
    0.53
    ":[{
    0.50
    bish
    0.48
    érique
    0.48
    DeleteMapping
    0.47
    getSimpleName
    0.46
    ünkü
    0.45
    gebene
    0.45
    __':
    0.45
    ériques
    0.45
    Activations Density 0.368%

    No Known Activations