© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 4840
    Prev
    Next
    INDEX
    Explanations

    words relating to asking questions in an online context

    oai_token-act-pair · gemini-2.0-flash

    Chat logs

    np_max-act · gemini-2.0-flash

    plus

    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_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     disambiguazione
    -0.74
     Houſe
    -0.70
     ſche
    -0.68
     fubject
    -0.67
     Sado
    -0.65
     houſe
    -0.64
    Rüyada
    -0.63
    CGContext
    -0.62
     Chriftian
    -0.62
    cerely
    -0.62
    POSITIVE LOGITS
     the
    0.61
     an
    0.56
     it
    0.56
     assin
    0.54
     a
    0.52
    ram
    0.52
     his
    0.51
     another
    0.50
     this
    0.49
    hi
    0.49
    Activations Density 0.289%

    No Known Activations