© 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. 14754
    Prev
    Next
    INDEX
    Explanations

    uses of the word "getText","setText","Integer","Double","parseInt". A common programing usage

    oai_token-act-pair · gemini-2.0-flash

    obscure or archaic words

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

    say (

    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
    ()
    -0.77
    tt
    -0.66
    1
    -0.66
     
    -0.63
     ()
    -0.61
    5
    -0.61
    x
    -0.61
    li
    -0.60
    v
    -0.59
    b
    -0.59
    POSITIVE LOGITS
     itſelf
    1.29
     Efq
    1.27
     raiſ
    1.26
     Monfieur
    1.23
     Theſe
    1.23
     myſelf
    1.21
    NUMX
    1.16
     purpoſe
    1.14
     faſt
    1.14
     avoient
    1.13
    Activations Density 7.784%

    No Known Activations