© 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. 15053
    Prev
    Next
    INDEX
    Explanations

    polite conversational filler words and phrases and words indicating confusion or doubt.

    oai_token-act-pair · gemini-2.0-flash

    programming language keywords or function names

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

    ,

    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
     dear
    -0.97
     mate
    -0.86
     bro
    -0.84
     guys
    -0.81
     sir
    -0.81
     Dear
    -0.80
     buddy
    -0.79
     dude
    -0.76
     señores
    -0.75
     Guys
    -0.71
    POSITIVE LOGITS
    LookAnd
    1.23
     Савезне
    1.02
     дописавши
    0.96
    awtextra
    0.94
    脚注の使い方
    0.91
    ReusableCell
    0.91
     CreateTagHelper
    0.88
    :+:
    0.87
    MigrationBuilder
    0.87
    MessageOf
    0.86
    Activations Density 0.498%

    No Known Activations