© 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. 11681
    Prev
    Next
    INDEX
    Explanations

    words related to purchasing and selling tickets

    oai_token-act-pair · gemini-2.0-flash

    tickets

    np_max-act-logits · 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
    Personendaten
    -0.66
     Selva
    -0.65
    цездатний
    -0.63
     consultato
    -0.62
    HtmlAttribute
    -0.61
    tagez
    -0.60
    EndInit
    -0.60
     محفوظة
    -0.59
    دانشنامهٔ
    -0.59
    NUMX
    -0.59
    POSITIVE LOGITS
     box
    0.59
     Box
    0.48
    box
    0.48
    BOX
    0.46
     BOX
    0.46
    กรณ์
    0.44
    Box
    0.43
     boxes
    0.43
     informação
    0.41
    <?
    0.41
    Activations Density 1.595%

    No Known Activations