© 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. 15332
    Prev
    Next
    INDEX
    Explanations

    personal pronouns and auxiliary verbs and adjectives that describe quantity

    oai_token-act-pair · gemini-2.0-flash

    Authority/being wronged

    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
    MigrationBuilder
    -0.58
    writerow
    -0.58
    webElementGuid
    -0.57
    woj
    -0.54
    jsxFileName
    -0.54
     WaitForSeconds
    -0.54
    ɵɵelementStart
    -0.53
    opsida
    -0.53
    SaveChangesAsync
    -0.53
    setVerticalGroup
    -0.53
    POSITIVE LOGITS
     EconPapers
    0.62
    ритори
    0.61
     الرياضيه
    0.61
    StructEnd
    0.57
    äumt
    0.51
     degradability
    0.49
    colhead
    0.47
    bledon
    0.47
     Promoted
    0.46
    Jîn
    0.46
    Activations Density 2.052%

    No Known Activations