© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 7714
    Prev
    Next
    INDEX
    Explanations

    patterns about people making a journey in the past

    oai_token-act-pair · gemini-2.0-flash

    forms of the verb "join"

    np_token-act-pair-logits · gpt-4o-mini

    joining

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    sizeCache
    -0.68
    Tikang
    -0.66
    UnknownFieldSet
    -0.64
    Fli
    -0.62
     SEDS
    -0.62
     defaultstate
    -0.61
     flipping
    -0.60
    CloseOperation
    -0.59
    LayoutStyle
    -0.59
    حياته
    -0.58
    POSITIVE LOGITS
     join
    0.90
     joined
    0.81
    join
    0.79
     Join
    0.75
    Join
    0.75
     joins
    0.71
    JOIN
    0.69
     joining
    0.68
     JOIN
    0.67
     rejoined
    0.65
    Activations Density 1.162%

    No Known Activations