© 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. 11957
    Prev
    Next
    INDEX
    Explanations

    conversational language, especially direct quotes

    oai_token-act-pair · gemini-2.0-flash

    CMT

    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
     AttributeSet
    -0.91
    Diwedd
    -0.85
    :✨
    -0.84
     consultato
    -0.82
     дописавши
    -0.81
    modelBuilder
    -0.80
     blessés
    -0.78
     يتيمه
    -0.77
    Билгалдахарш
    -0.75
     wikipagina
    -0.74
    POSITIVE LOGITS
     CMT
    0.36
    —-
    0.36
    -------------</
    0.35
    thmus
    0.35
     alum
    0.34
     Sua
    0.34
    >
    0.34
    ---
    0.34
    ---
    0.33
    rend
    0.33
    Activations Density 3.252%

    No Known Activations