© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 15686
    Prev
    Next
    INDEX
    Explanations

    the uppercase letter "D"

    oai_token-act-pair · gemini-2.0-flash

    D

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    XmlIgnore
    -0.52
    AutoScaleMode
    -0.52
    ViewChild
    -0.51
     chloro
    -0.51
    ,$_
    -0.51
    enumii
    -0.50
     Advanced
    -0.47
    ----|
    -0.46
    ſelf
    -0.46
    wachsenen
    -0.46
    POSITIVE LOGITS
    latego
    0.69
    MigrationBuilder
    0.66
    NameInMap
    0.56
     protoimpl
    0.56
    MENAFN
    0.54
     BrowserModule
    0.53
    ništ
    0.52
     Roskov
    0.52
     SwitchCompat
    0.52
    tvguidetime
    0.52
    Activations Density 0.377%

    No Known Activations