© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6045
    Prev
    Next
    INDEX
    Explanations

    words and numbers relating to velocity and speed

    oai_token-act-pair · gemini-2.0-flash

    speed/velocity

    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
    MigrationBuilder
    -0.44
     ويكيميديا
    -0.43
     inner
    -0.43
     б
    -0.42
    enumi
    -0.41
    Path
    -0.41
     route
    -0.40
    direct
    -0.40
     inside
    -0.40
     direct
    -0.40
    POSITIVE LOGITS
    IntoConstraints
    0.79
     createSprite
    0.75
     supersonic
    0.71
    ScopeManager
    0.66
    sound
    0.66
     Monfieur
    0.65
     faſt
    0.65
     Shakspeare
    0.64
     pleaſure
    0.63
     sound
    0.63
    Activations Density 1.000%

    No Known Activations