© 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. 2205
    Prev
    Next
    INDEX
    Explanations

    the word 'live' followed by media-related terms like streaming or video

    oai_token-act-pair · gemini-2.0-flash

    terms related to live streaming

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

    live events and broadcasts

    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
    avigation
    -0.43
    üyor
    -0.43
    jspx
    -0.42
    ")));
    -0.41
     ThemeData
    -0.41
    Distributed
    -0.40
     tén
    -0.40
    сихо
    -0.40
    )]$
    -0.40
     _)
    -0.40
    POSITIVE LOGITS
    TagMode
    0.83
    mybatisplus
    0.74
    TagHelper
    0.70
    SequentialGroup
    0.67
     CURIAM
    0.63
    ISupport
    0.63
     propOrder
    0.62
    TagHelpers
    0.60
    SuppressLint
    0.60
    ITURE
    0.59
    Activations Density 0.545%

    No Known Activations