© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 13737
    Prev
    Next
    INDEX
    Explanations

    first-person speech expressing an opinion or difficulty

    oai_token-act-pair · gemini-2.0-flash

    forms of "can"

    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
     Cannot
    -1.41
    cannot
    -1.35
     impossibility
    -1.34
     couldn
    -1.34
     couldnt
    -1.31
     impossible
    -1.29
     Couldn
    -1.28
     cannot
    -1.28
     unable
    -1.25
    couldn
    -1.22
    POSITIVE LOGITS
     can
    1.26
    can
    0.82
     peuvent
    0.70
     dapat
    0.68
     bisa
    0.68
     Can
    0.67
    可以
    0.66
    Can
    0.65
     können
    0.64
     pueden
    0.60
    Activations Density 1.873%

    No Known Activations