© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6549
    Prev
    Next
    INDEX
    Explanations

    the word "responsibility" and short fragments of the word in various tenses

    oai_token-act-pair · gemini-2.0-flash

    respon

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     estekak
    -0.73
    ]--;
    -0.68
    ]:
    -0.66
    ]++;
    -0.66
     ProtoMessage
    -0.65
    AutoScale
    -0.65
     تضيفلها
    -0.65
    tagext
    -0.65
    gameserver
    -0.62
    Rhestr
    -0.62
    POSITIVE LOGITS
    insee
    0.55
    cydow
    0.47
    sibilities
    0.47
     consol
    0.47
    disi
    0.46
    исленность
    0.46
    medriver
    0.46
    structors
    0.45
     שוליים
    0.44
    RestController
    0.44
    Activations Density 0.815%

    No Known Activations