© 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. 2091
    Prev
    Next
    INDEX
    Explanations

    something about production processes and raw materials or past tense verbs and nouns

    oai_token-act-pair · gemini-2.0-flash

    Raw materials

    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
    ValueStyle
    -0.73
     الرياضيه
    -0.62
    Naissance
    -0.57
    ToAction
    -0.57
    NamedQuery
    -0.56
    tagHelperRunner
    -0.55
    PhysRevD
    -0.54
    économ
    -0.53
     NSCoder
    -0.52
     resourceCulture
    -0.52
    POSITIVE LOGITS
     input
    1.27
     inputs
    1.20
     ingredients
    1.16
     raw
    1.13
     Input
    1.11
     ingredient
    1.06
    input
    1.05
    Input
    1.04
     materials
    1.00
     Inputs
    0.97
    Activations Density 3.347%

    No Known Activations