© 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. 9405
    Prev
    Next
    INDEX
    Explanations

    a mix of words expressing shifts of perspective and potentially counter-argumentation.

    oai_token-act-pair · gemini-2.0-flash

    changes, improvements

    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
     Lightboxes
    -0.66
    なんとか
    -0.63
    RenderAtEndOf
    -0.63
     pourtant
    -0.62
     luckily
    -0.61
     salvage
    -0.61
    LookAnd
    -0.60
    だけは
    -0.59
     compensatory
    -0.59
     thankfully
    -0.58
    POSITIVE LOGITS
     TextAppearance
    0.65
    PRNewswire
    0.57
    UseVisualStyle
    0.50
     inégal
    0.48
     préférable
    0.46
     kemenangan
    0.46
    RRect
    0.45
     Optimum
    0.44
    Contributed
    0.44
    Xaml
    0.44
    Activations Density 4.014%

    No Known Activations