© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 584
    Prev
    Next
    INDEX
    Explanations

    words related to length, quantities, location, and present tense verbs.

    oai_token-act-pair · gemini-2.0-flash

    Measurements and technical language

    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
     Large
    -1.35
    Large
    -1.35
     large
    -1.33
    large
    -1.31
    Small
    -1.24
     Low
    -1.23
    small
    -1.20
    Low
    -1.20
     Small
    -1.18
     low
    -1.14
    POSITIVE LOGITS
    原始内容存档于
    0.79
     BrowserModule
    0.70
    UseVisualStyle
    0.68
    formik
    0.60
     TestBed
    0.60
    mobileqq
    0.56
    awaiter
    0.56
     يتيمه
    0.55
    PreAuthorize
    0.55
    SuppressLint
    0.54
    Activations Density 3.418%

    No Known Activations