© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 12365
    Prev
    Next
    INDEX
    Explanations

    opinions and discussion

    oai_token-act-pair · gemini-2.0-flash

    see

    np_max-act · gemini-2.0-flash

    see

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     seeing
    -0.68
     sighting
    -0.67
     seen
    -0.65
     witness
    -0.65
     witnessing
    -0.63
     witnessed
    -0.62
     see
    -0.62
     sightings
    -0.61
     saw
    -0.60
     witnesses
    -0.59
    POSITIVE LOGITS
    Gizmos
    0.50
    нциклопедия
    0.47
    BagConstraints
    0.46
    BeforeAll
    0.46
    řeb
    0.45
    ่วน
    0.43
    ագր
    0.42
     caoutchouc
    0.42
    stateProvider
    0.42
    inginan
    0.42
    Activations Density 9.025%

    No Known Activations