© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 4948
    Prev
    Next
    INDEX
    Explanations

    code related to Android UI widgets

    oai_token-act-pair · gemini-2.0-flash

    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_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     Efq
    -0.94
     itſelf
    -0.91
     Theſe
    -0.91
     myſelf
    -0.91
     ſtate
    -0.90
     ſeveral
    -0.85
    ^(@)
    -0.85
     themſelves
    -0.84
     pleaſure
    -0.84
     ainfi
    -0.82
    POSITIVE LOGITS
    â
    0.46
    HttpFoundation
    0.41
    SourceChecksum
    0.40
    CJK
    0.39
     مُعرِّف
    0.35
    исленность
    0.35
    g
    0.34
    BackgroundColor
    0.34
     بر
    0.34
     ModelExpression
    0.34
    Activations Density 3.385%

    No Known Activations