© 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. 3660
    Prev
    Next
    INDEX
    Explanations

    forms of the word "rely"

    oai_token-act-pair · gemini-2.0-flash

    say "on"

    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
     Theſe
    -0.90
     avoient
    -0.84
    EFIAPI
    -0.81
     Efq
    -0.81
     Jefus
    -0.81
     Monfieur
    -0.80
     auroit
    -0.79
     $_"
    -0.79
     onCreateView
    -0.78
    TagMode
    -0.77
    POSITIVE LOGITS
    rest
    0.47
    I
    0.44
    U
    0.44
     sti
    0.41
     I
    0.39
    p
    0.39
    pre
    0.39
     up
    0.39
     p
    0.38
    mar
    0.37
    Activations Density 3.036%

    No Known Activations