© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 2396
    Prev
    Next
    INDEX
    Explanations

    mentions of conversations or discussions involving multiple stakeholders

    oai_token-act-pair · gemini-2.0-flash

    conversation, discussion

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     limón
    -0.48
    getRuntime
    -0.48
    Submitted
    -0.47
    chauen
    -0.46
     Bogen
    -0.45
     Tuan
    -0.44
     voyez
    -0.44
    centaje
    -0.43
     typelib
    -0.42
    aryti
    -0.42
    POSITIVE LOGITS
     chat
    1.53
     talk
    1.52
     talks
    1.34
     chats
    1.34
     discussion
    1.34
     conversation
    1.31
     discuss
    1.30
    talk
    1.28
     Talk
    1.26
     talked
    1.23
    Activations Density 1.281%

    No Known Activations