© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6770
    Prev
    Next
    INDEX
    Explanations

    a variety of common words in the English language, but often in seemingly related clusters.

    oai_token-act-pair · gemini-2.0-flash

    Black color

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     yellows
    -0.80
     yellow
    -0.71
     whiteness
    -0.67
    errHandler
    -0.65
     xenia
    -0.63
    yellow
    -0.61
     jaune
    -0.60
     Reſ
    -0.59
     }}"></
    -0.59
     whites
    -0.59
    POSITIVE LOGITS
     pitch
    0.81
     jet
    0.74
    pitch
    0.67
    Jet
    0.64
    Pitch
    0.63
     Jet
    0.63
    jet
    0.63
     Pitch
    0.57
     atra
    0.54
     black
    0.53
    Activations Density 0.702%

    No Known Activations