© 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. 11622
    Prev
    Next
    INDEX
    Explanations

    the word "ingredients", and to a lesser extent also "assumptions" and also when the pronoun "it" appears near the words "solvent" and "ingredient"

    oai_token-act-pair · gemini-2.0-flash

    ingredients

    np_max-act · gemini-2.0-flash
    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
     McIn
    -0.70
    s
    -0.69
    ة
    -0.67
    ávají
    -0.66
    ranging
    -0.63
     adsorption
    -0.59
    setColumns
    -0.59
     profunda
    -0.58
     Altos
    -0.58
     Kers
    -0.58
    POSITIVE LOGITS
    tagHelperRunner
    0.89
    IVersion
    0.78
    __))
    0.78
     propOrder
    0.75
     Roskov
    0.75
    paksa
    0.73
    ragalactic
    0.70
    Autoritní
    0.69
     Baillargeon
    0.66
    źdz
    0.65
    Activations Density 2.236%

    No Known Activations