© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 2356
    Prev
    Next
    INDEX
    Explanations

    words related to physical properties and scientific measurements

    oai_token-act-pair · gemini-2.0-flash

    Engines and rotation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     my
    -0.53
     two
    -0.49
     me
    -0.48
     kasarigan
    -0.46
    two
    -0.46
    久的
    -0.46
     minh
    -0.45
    amzn
    -0.44
    ry
    -0.44
     her
    -0.44
    POSITIVE LOGITS
    ArgsConstructor
    0.82
    ConstraintMaker
    0.79
    HtmlAttribute
    0.77
    EDEFAULT
    0.76
     صوتيه
    0.71
     crdi
    0.69
     MotionEvent
    0.68
    TestingModule
    0.68
     protoimpl
    0.66
    UIControlState
    0.66
    Activations Density 1.891%

    No Known Activations