© 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. 8488
    Prev
    Next
    INDEX
    Explanations

    recipes or cooking instructions, especially ingredients and actions

    oai_token-act-pair · gemini-2.0-flash

    Salts and powders

    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
     PyLong
    -0.68
     <<<<<<<<<<<<<<
    -0.63
    (!__
    -0.60
    LookAnd
    -0.59
     resourceCulture
    -0.55
    úrate
    -0.54
     initWithFrame
    -0.53
     Washington
    -0.52
     Sui
    -0.52
     Btu
    -0.52
    POSITIVE LOGITS
     salt
    1.06
     powder
    0.88
    salt
    0.86
     salts
    0.82
     Salt
    0.79
    Salt
    0.79
     Powder
    0.75
    powder
    0.72
     polvere
    0.71
    Powder
    0.70
    Activations Density 0.826%

    No Known Activations