© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10073
    Prev
    Next
    INDEX
    Explanations

    Croatian language text related to Facebook account verification and SMS fees

    oai_token-act-pair · gemini-2.0-flash

    account confirmations

    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
     I
    -0.46
    rh
    -0.41
    how
    -0.41
    mh
    -0.41
    redux
    -0.40
    í
    -0.40
    ミア
    -0.40
    िर
    -0.39
    僕も
    -0.39
    ,
    -0.39
    POSITIVE LOGITS
     Мексичка
    0.82
    Hentet
    0.81
     '\\;'
    0.75
     Chwiliwch
    0.75
    脚注の使い方
    0.73
    uxxxx
    0.71
     utafitiHapana
    0.71
     дописавши
    0.70
    moiselle
    0.69
    èdia
    0.68
    Activations Density 0.141%

    No Known Activations