© 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. 9777
    Prev
    Next
    INDEX
    Explanations

    terms related to Android UI layout and XML

    oai_token-act-pair · gemini-2.0-flash

    technical terms or identifiers

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

    Android UI code

    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
     bezeichneter
    -0.61
    ❋
    -0.56
     genus
    -0.56
    género
    -0.56
    ⎧
    -0.53
    PARATION
    -0.51
    ächtigen
    -0.51
     Houſe
    -0.51
    huawei
    -0.50
     vapeur
    -0.50
    POSITIVE LOGITS
     betweenstory
    0.82
    LookAnd
    0.68
    webElementXpaths
    0.59
     nahilalakip
    0.58
    RegressionTest
    0.57
    Geplaatst
    0.54
    AddTagHelper
    0.54
    Personendaten
    0.53
    transQ
    0.52
     createSlice
    0.50
    Activations Density 6.845%

    No Known Activations