© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 5365
    Prev
    Next
    INDEX
    Explanations

    personal opinions and assumptions

    oai_token-act-pair · gemini-2.0-flash

    making assumptions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    ⓘ
    -0.80
    LEncoder
    -0.72
    fromnode
    -0.62
    IntoConstraints
    -0.62
    onOptions
    -0.61
    enderror
    -0.60
     itſelf
    -0.60
    AnchorStyles
    -0.60
     AssemblyTitle
    -0.59
     tofu
    -0.58
    POSITIVE LOGITS
     assume
    1.41
     guess
    1.35
     presume
    1.24
     assumption
    1.21
     guessing
    1.20
     assumes
    1.15
     suspect
    1.14
     Guess
    1.13
     suppose
    1.13
    guess
    1.13
    Activations Density 1.313%

    No Known Activations