© 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. 6950
    Prev
    Next
    INDEX
    Explanations

    Java code

    oai_token-act-pair · gemini-2.0-flash

    French words

    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
    ↵↵
    -0.55
    4
    -0.53
    filepath
    -0.51
    index
    -0.50
     hat
    -0.49
    os
    -0.49
    top
    -0.49
    ho
    -0.48
    ...
    -0.47
    cup
    -0.47
    POSITIVE LOGITS
     avoient
    0.95
     étoient
    0.90
     quelcon
    0.86
     démocr
    0.82
     plufieurs
    0.81
     ainfi
    0.80
     feroit
    0.80
     auroit
    0.79
    tvguidetime
    0.79
     enfans
    0.79
    Activations Density 0.694%

    No Known Activations