© 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. 13612
    Prev
    Next
    INDEX
    Explanations

    information about taking an exam

    oai_token-act-pair · gemini-2.0-flash

    technical documentation/help forum

    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
     '\\;'
    -0.94
     تضيفلها
    -0.90
     oprot
    -0.82
    ChildScrollView
    -0.81
    AsUp
    -0.81
    ollectionView
    -0.78
     ModelExpression
    -0.78
    ########.
    -0.77
    principalColumn
    -0.77
    WriteBarrier
    -0.76
    POSITIVE LOGITS
     n
    0.75
     &
    0.65
     "
    0.56
     specially
    0.56
     “
    0.55
     meanwhile
    0.54
     so
    0.53
     for
    0.52
     particularly
    0.52
     call
    0.51
    Activations Density 9.610%

    No Known Activations