© 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. 11722
    Prev
    Next
    INDEX
    Explanations

    escape characters that represent newline, carriage return and tab

    oai_token-act-pair · gemini-2.0-flash

    Code and errors

    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
    findpost
    -0.77
     sclerosis
    -0.61
    NegativeButton
    -0.60
    abetes
    -0.60
     disambiguazione
    -0.59
    uyez
    -0.57
    routeProvider
    -0.57
    parsedMessage
    -0.57
     صوتيه
    -0.57
    DeleteBehavior
    -0.54
    POSITIVE LOGITS
    neté
    0.53
     henvisninger
    0.49
     typelib
    0.48
     onBind
    0.46
    glTranslatef
    0.46
     localVar
    0.44
    Shallow
    0.43
    robial
    0.43
     writeTo
    0.43
     setting
    0.43
    Activations Density 0.175%

    No Known Activations