© 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. 2235
    Prev
    Next
    INDEX
    Explanations

    dialogue from a queen and execution events

    oai_token-act-pair · gemini-2.0-flash

    code-related technical 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
    或
    -0.45
    THEOREM
    -0.42
    一家
    -0.41
     sklearn
    -0.41
     serializers
    -0.41
     or
    -0.41
    x
    -0.40
    ě
    -0.40
    8
    -0.40
    بوابة
    -0.39
    POSITIVE LOGITS
    PerformLayout
    0.86
    AndEndTag
    0.77
    IntoConstraints
    0.76
     صوتيه
    0.73
    DeleteBehavior
    0.72
    ">//
    0.71
    发表于
    0.70
     CanadaChoose
    0.69
    exitRule
    0.68
     Efq
    0.68
    Activations Density 5.487%

    No Known Activations