© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 9203
    Prev
    Next
    INDEX
    Explanations

    text discussing choices, experiences, and agency

    oai_token-act-pair · gemini-2.0-flash

    self-reflection, choices

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     rospy
    -0.66
     Shakspeare
    -0.61
     phosphory
    -0.60
     pleaſure
    -0.60
     QName
    -0.59
     hObject
    -0.59
     kasarigan
    -0.57
     Roskov
    -0.57
     Claro
    -0.56
     CURIAM
    -0.56
    POSITIVE LOGITS
     autorytatywna
    0.44
     बजाय
    0.42
     invece
    0.42
    ：“……”
    0.41
    typeof
    0.41
     levé
    0.41
    WithIOException
    0.40
    Traducción
    0.40
    perate
    0.40
    IsContent
    0.40
    Activations Density 1.343%

    No Known Activations