© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 12719
    Prev
    Next
    INDEX
    Explanations

    text about power supplies and electric current, especially in medical or sensitive contexts.

    oai_token-act-pair · gemini-2.0-flash

    motors

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    breos
    -0.57
    asteroide
    -0.55
     laine
    -0.53
     poils
    -0.52
    WEEN
    -0.51
     rayures
    -0.50
     Verlags
    -0.50
    opar
    -0.46
    Oneof
    -0.46
     élas
    -0.45
    POSITIVE LOGITS
     motor
    0.69
     motors
    0.63
    esModule
    0.63
    BufferException
    0.62
     Motor
    0.60
    motor
    0.60
     fuses
    0.59
    Motor
    0.56
     <<<<<<<<<<<<<<
    0.55
     dAtA
    0.54
    Activations Density 7.218%

    No Known Activations