© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 9463
    Prev
    Next
    INDEX
    Explanations

    words related to cheese and cheeseburgers

    oai_token-act-pair · gemini-2.0-flash

    types of cheese

    np_token-act-pair-logits · gpt-4o-mini

    cheese

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    ">//
    -0.60
    hoeddwyd
    -0.54
    InputTagHelper
    -0.54
    WithIOException
    -0.53
    enumi
    -0.51
    WriteTagHelper
    -0.49
    Tikang
    -0.49
     Musa
    -0.47
     "..\..\
    -0.47
     utafitiHapana
    -0.46
    POSITIVE LOGITS
    новништво
    0.68
    Brie
    0.67
     Che
    0.65
     brie
    0.61
    Che
    0.60
     kaas
    0.59
    Kä
    0.58
    omitempty
    0.58
     Gruy
    0.57
     Brie
    0.56
    Activations Density 0.934%

    No Known Activations