© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 2302
    Prev
    Next
    INDEX
    Explanations

    comment headers, certain conjunctions, and game-related terms within online discussions, possibly indicating engagement or contribution to the conversation

    oai_token-act-pair · gemini-2.0-flash

    Web page comments

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    SourceChecksum
    -0.48
    THISDAY
    -0.44
     avven
    -0.44
     bianche
    -0.44
     transférez
    -0.43
    With
    -0.42
    I
    -0.41
    行政区划
    -0.41
    with
    -0.40
     bisogno
    -0.39
    POSITIVE LOGITS
    terness
    0.60
     Puck
    0.60
    drawal
    0.56
    uesday
    0.56
    smoke
    0.55
    NewUrlParser
    0.54
     Ender
    0.54
    drip
    0.53
    าก็
    0.53
    shooter
    0.53
    Activations Density 22.316%

    No Known Activations