© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12509
    Prev
    Next
    INDEX
    Explanations

    the word "disk" and related concepts about computer storage

    oai_token-act-pair · gemini-2.0-flash

    disk

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    <bos>
    -1.13
     disk
    -0.85
     Disk
    -0.75
    WriteTagHelper
    -0.72
     disks
    -0.70
    disk
    -0.62
     disc
    -0.59
    Disk
    -0.57
    EndContext
    -0.56
    PreExecute
    -0.55
    POSITIVE LOGITS
    kuuta
    0.68
     correctes
    0.65
    -------
    0.65
    virons
    0.61
    jago
    0.60
    oredCriteria
    0.57
    Controllo
    0.56
    providedIn
    0.55
    WebElementEntity
    0.54
     يتيمه
    0.54
    Activations Density 0.771%

    No Known Activations