© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12074
    Prev
    Next
    INDEX
    Explanations

    lines of poetry that express uncertainty and questioning

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    Geplaatst
    -1.05
     kasarigan
    -0.93
    حوالہ
    -0.77
    ResumeLayout
    -0.73
    CloseOperation
    -0.73
    Билгалдахарш
    -0.72
     disambiguazione
    -0.69
     esternos
    -0.66
    HomeAsUpEnabled
    -0.66
    SharedDtor
    -0.61
    POSITIVE LOGITS
     ’
    0.66
    /******/
    0.50
    batore
    0.47
     '
    0.47
     ‘
    0.40
     meth
    0.40
    pieler
    0.40
     hombro
    0.40
    休
    0.39
     o
    0.39
    Activations Density 1.522%

    No Known Activations