© 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. 2520
    Prev
    Next
    INDEX
    Explanations

    the prefix "di"

    oai_token-act-pair · gemini-2.0-flash

    di

    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
    UnsafeEnabled
    -0.55
    BagLayout
    -0.55
     IBOutlet
    -0.54
    ValueStyle
    -0.52
    "]);
    -0.52
     raiſ
    -0.52
     continúas
    -0.52
     يتيمه
    -0.51
     لينك
    -0.51
     tiguan
    -0.50
    POSITIVE LOGITS
    RegistryLite
    0.63
     &___
    0.59
    原始内容存档于
    0.59
    oa̍t
    0.59
    segna
    0.52
     Roskov
    0.50
    Rptr
    0.49
    jetivo
    0.48
    providedIn
    0.47
    libft
    0.47
    Activations Density 5.049%

    No Known Activations